FAQs for EyeDetect, the best lie detector on the market, and IdentityDetect, the fastest way to find out if someone is lying about who they are.
FAQs for EyeDetect | Converus - The eyes don't lie®
General Questions - EyeDetect and EyeDetect+
EyeDetect is the world’s first technology to accurately detect lies in 15 to 30 minutes by analyzing eye behavior. It’s also cost-effective, efficient and secure.
First conceived in 2002, it’s the first ocular-motor deception detection test. The same scientists that invented the computerized polygraph in 1991 also developed EyeDetect. In September 2013, the technology was given the brand name “EyeDetect.”
EyeDetect is a new way for organizations to manage risk and create workplace integrity. It helps law enforcement agencies and governments find liars. Ultimately, it helps protect countries, corporations and communities from corruption, fraud and threats.
EyeDetect+ is the convergence of standard EyeDetect equipment + polygraph sensors and testing techniques. It’s the world’s first automated polygraph. It makes lie detection testing impartial, accurate and less intrusive than a traditional polygraph. It assesses credibility by measuring, recording, and analyzing involuntary eye behaviors and physiological changes.
EyeDetect+ is an automated polygraph. As such, it is:
- Impartial — EyeDetect equipment performs test administration and an advanced algorithm analyzes and scores the test data reliably (100% consistently). A traditional polygraph exam is scored by a human, who can potentially make mistakes.
- Accurate — The testing protocol combines measuring and recording physiological changes (polygraph) and oculomotor measures (EyeDetect) with test questioning techniques into a single test. It uses the most diagnostic data to calculate a credibility score.
- Less intrusive — It replaces the most intrusive polygraph sensor, the blood pressure arm cuff, with two small wrist sensors. Also, a strain gauge(s) is used instead of a pneumograph. And, testing time is 40 minutes or less, causing less examinee fatigue.
These features make EyeDetect+ one of the most comprehensive, reliably accurate and effective lie detectors ever invented.
How accurate is EyeDetect?
To see a summary of research, including peer-reviewed articles, click here.
In April 2020, Dr. Andrew Potts published the results of a lab study conducted at the University of Utah with a new multi-issue comparison test (MCT) protocol. In that study, EyeDetect achieved two amazing milestones: (1) 88% accuracy and (2) the capability of scoring up to 4 relevant issues in a single test.
In the European Polygraph Journal (Dec. 2016), Dr. John Kircher and Dr. David Raskin reported that when used for screening tests, EyeDetect is 88% accurate (based on field studies).
As an anecdotal example, Converus tested 66 polygraph examiners attending the American Polygraph Association (APA) seminar in Baltimore in 2016 with an EyeDetect number test. Of the 66 tests administered, EyeDetect determined the correct number 63 times. That is an accuracy rate of 95.5%. Tests were administered in English, Spanish and Arabic. Note: The probability of randomly guessing the correct number would be 1 of 8 or 12.5%.
All tests have error rates. For every 100 guilty or 100 innocent people tested, EyeDetect accurately classifies 88 people in screening tests and 90 in diagnostic tests. That means it inaccurately classifies 12 out of 100 people in screening tests and 10 out of 100 in diagnostic testing.
The Converus Science Team continues to look for ways to improve accuracy. Data from new lab and field studies help optimize the algorithm to increase overall accuracy.
How accurate is EyeDetect?
To see a summary of research, including peer-reviewed articles, click here.
In June 2021, Dr. John Kircher published the results of two lab studies on a Hybrid Multi-Issue Comparison Test (MCT) protocol and a Hybrid Directed Lie Comparison (DLC) Test. The term “hybrid” refers to a combination of ocular-motor and polygraph physiology measures and question formats. In those studies, EyeDetect achieved two milestones: (1) 88% accuracy for the Hybrid DLC and (2) 91% accuracy for the Hybrid MCT. The DLC format is used for specific issue tests (investigations primarily) and the MCT format is used for screening tests.
No, they are different solutions. EyeDetect+ is an automated polygraph that meets the needs of customers who are required to use polygraph for deception detection. The original EyeDetect system was released in 2014 and filled the need for a fast, accurate, affordable, noninvasive, or noncontact lie detection test. It continues to fill this need. EyeDetect detects deception by tracking involuntary changes in eye and reading behavior. More than 600 customers worldwide currently use EyeDetect for screening tests and investigative needs.
EyeDetect+ was developed for customers that require polygraph or where the law defines “lie detector” as polygraph. EyeDetect+ combines the measurement and scoring of diagnostic eye behaviors with the physiological activities of polygraph. It should meet the needs of polygraph examiners who monitor and score the same physiological activity.
Any organization that chooses to use polygraph or is required by law to screen job candidates, test current employees, or to conduct investigations. EyeDetect+ provides a way to conduct the same testing with an automated, faster process and a less intrusive test.
In 2002, John C. Kircher and his colleague, Doug Hacker, an educational psychologist with expertise in the psychology of reading, first discussed whether changes in eye movements and pupil size while reading and answering questions about a crime would reveal deception.
They wondered: “Would changes in cognitive load affect the eye in such a way that we can capture those changes and be as accurate as the polygraph in predicting whether or not someone is being deceptive?” At that time, the ocular-motor deception test (ODT) was born — later to be branded as EyeDetect.
In 2003, Kircher and Hacker, along with other cognitive scientists, Anne Cook and Dan Woltz, formed the Converus Science Team. They worked together to produce and validate this new lie detector. Dr. David C. Raskin joined the science team in 2009.
Kircher and Raskin are internationally known and highly respected scientists in the polygraph community. They frequently consult and lecture on the subject, as well as provide guidance to the polygraph community, government agencies, legislatures, and the courts.
They first published research on polygraph in the 1970s and then spent 10 years developing the software/hardware for the world’s first computerized polygraph system, which they marketed in 1991. They recognized the need to find new lie detectors that could complement the polygraph because the polygraph primarily measures emotional responses, not concealed knowledge.
In April 2014, after more than 10 years fine-tuning the technology, EyeDetect was introduced to the market.
Dr. Kircher embarked in 2020 to research and develop a new technology and testing protocol that combined ocular-motor testing methods and technology with existing polygraph solutions. This was partially done in response to requests from customers around the world where policy or government regulation requires the use of polygraph in deception detection testing.
The original premise was to determine the feasbility of combining the two most accurate lie detectors in the world into one solution—EyeDetect and polygraph.
After a lenghthy but successful R&D process, Dr. Kircher and his team developed EyeDetect+, the world’s first automated polygraph.
As the research began, Dr. Kircher felt compelled find a solution with characteristics that had made EyeDetect appealing:
- Less invasive for the examinee
- Reliable (consistent in obtaining high levels of accuracy
One of the most uncomfortable (invasive) components of a polygraph examination is the blood pressure cuff. It is used to measure and record blood pressure changes to help render a decision on the examinee’s truthfulness. Research shows there is a correlation between blood pressure changes and deception.
The duration of a polygraph exam is affected by the blood pressure cuff used. It must be deflated about every 5 minutes to restore circulation to the examinee’s arm. Otherwise, examinees can become distracted by the pain of the pressure, or tingling of the fingers or, in some cases, broken blood vessels. For this reason, the examiner allows the examinee many rest periods during a polygraph exam to alleviate the discomfort.
Dr. Kircher analyzed a variety of alternative technologies to eliminate the blood pressure cuff. One such method considered was Pulse Transit Time (PTT). PTT is defined as the time it takes a pulse wave to travel from the heart to the finger. Dr. Andrea Webb looked at PTT in a study for her master’s thesis in 2006. In various other studies, PTT was shown to vary inversely with changes in blood pressure (Geddes et al., 1981; Obrist et al., 1978; Obrist et al., 1979).
By eliminating the blood pressure cuff, the EyeDetect+ test includes more questions than a traditional polygraph. More questions produce more measurements of physiological reactions and the additional measurements improve the reliability and accuracy of the test.
As mentioned, validity (accuracy) and reliability were also an important consideration in developing a new solution. EyeDetect+ and EyeDetect) rely on computer-based decision models and algorithms and, therefore, reliability is 100%. Why? The systematic and computerized application of the same decision rules to analyze testing data will yield reliable (consistent) results. The two factors were important considerations during Dr. Kircher’s research and development.
EyeDetect+ (and EyeDetect) tests are almost completely automated. As a result, test validity does not depend on the examiner to properly interpret physiological recordings. Because the test presentation and scoring are computerized, the examinee and examiner cannot influence the test outcome.
The Converus Science Team, led by Dr. John Kircher, has published 19 articles or reports about the technology underlying EyeDetect®. In the research, EyeDetect is referred to as an ocular-motor deception test (ODT). Currently, there are 10 peer-reviewed research articles on EyeDetect.
To see a summary of research, including peer-reviewed articles, click here.
EyeDetect uses a statistical method called a logistic regression equation to analyze eye behaviors and reading data. The data is measured and recorded by a high-definition camera that measures changes in pupil diameter and eye movements during a question and answer session with an examinee.
The test is automated and administered by a computer. After analyzing the examinee’s responses and the eye behavior data, a score is calculated, which is called the Converus Credibility Score.
Variables measured and recorded during the test include pupil dilation, question response accuracy, question response time, gaze fixation, blink rates, reading behavior, and some other variables. The purpose for analyzing various independent variables is to obtain a biologically reasonable answer to describe the test result: credible or deceptive.
The score used by EyeDetect intends to “maximize the likelihood” of the categorization of deceptive or credible. A Converus Credibility Score between 1 and 49 indicates deception. A score between 50 and 99 indicates credibility.
EyeDetect uses a statistical formula and gives a range of test scores. The closer the Credibility score is to 1, the likelihood of deception is maximized. The closer the score is to 99, the likelihood of credibility is maximized. If a person gets a Converus Credibility Score of 51, 52, 53, etc., the probability of credibility is minimal.
After an EyeDetect test is taken and scored, a test report is available in a web-based Dashboard within a few minutes. Any authorized person can access test reports through a Web browser, in any location, on any device. Decision makers can quickly see each person’s name, date/time, test taken and credibility score within minutes of test completion.
To learn more about the dashboard, click here.
In October 2009, a company called Credibility Assessment Technologies LLC was created to bring to market this new lie detector. In September 2013, the technology was given the brand name “EyeDetect.”
On December 12, 2013, the company was officially renamed Converus, Inc. The name Converus is derived from two Latin words: con (meaning “with”) and verus (meaning “truth”).The company is currently headquartered in Lehi, Utah, USA.
EyeDetect was admitted as evidence (Daubert motion) in a criminal sexual assault case in the 8th District Judicial Court, County of Taos, New Mexico. The trial was held May 2018. Mark Handler of Converus was the expert witness. The case was State of New Mexico (plaintiff) vs. John Rael (defendant) with Judge – Jeff F. McElroy.
EyeDetect Use and Applications
EyeDetect is used to screen job candidates and to conduct periodic testing of current employees. It can also be used for diagnostic, single-issue testing. Tests measure a person’s involvement in theft, fraud, stealing confidential information, money laundering, bribes, drug use, identity theft, violent crimes, ties to gangs or organized crime, receipt of inappropriate benefits at work, and many other topics.
EyeDetect can be used by governments to screen refugees and visa applicants, especially for the purpose of identifying those with ties to terrorism. It can also be used for parolee and offender screening, as well as others that may pose a threat to communities. And, it can be used in conducting criminal or civil case investigations.
EyeDetect tests takes 15 minutes for single issues tests and 30 minutes for multi-issue screening tests.
The EyeDetect+ test takes 20 minutes for single issues tests and 45 minutes for multi-issue screening tests.
In both cases, test reports and test scores are available in less than 5 minutes.
Standard training for test administrators and decision makers takes about 6 hours. Advanced training for test writers takes up to 2 additional days. Training to improve pre-test and post-test interviewing skills takes 1 day.
By comparison, polygraph examiners undergo 10 weeks of training and ongoing evaluation. (EyeDetect+ automatically scores tests with a computer algorithm; there is no requirement to interpret charts and to manually score tests, as is done with polygraph.)
EyeDetect can be used to test for issues of infidelity in a marriage, partnership, for those engaged to be married, or for those in an exclusive relationship.
In the U.S., EyeDetect can be used for screening or evaluating federal, state, or local government employees. This includes law enforcement and national security agencies. It can also be used for conducting investigations for criminal or civil cases.
Outside the U.S., EyeDetect is used in all types of organizations for pre-employment screening, periodic or maintenance testing, or diagnostic single-issue tests. Tests measure an applicant’s or employee’s involvement in theft, fraud, money laundering, bribes, drug use, identity theft, stealing confidential information, violent crimes, having ties to gangs or organized crime, receipt of inappropriate benefits at work, and many other topics.
Yes. If a diagnostic (single issue test) follows a screening test with a one-hour recess in between, the examinee should be capable and able to take a second test.
Any substance, medication or brain injury that adversely affects reaction time, eye movement, or pupil dilation can affect comprehension, eye behavior, and cognitive load. For example, it is best not to test someone that is intoxicated.
Diagnostic Testing for Pupillary and Cognitive Responses
Converus provides two optional, diagnostic tests as part of the EyeDetect testing process. These two tests can help ensure an examinee has normal pupillary responses and demonstrates changes in cognitive load while testing. If not, the examinee may have had a traumatic brain injury or is using medications or eye drops to affect eye behavior. There is scientific research to validate both tests.
Pupillary Light Reflex Diagnostic
This test is used to assess brain stem function. If reactions are abnormal, that suggests optic nerve injury, oculomotor nerve damage, brain stem lesions, such as tumors, or use of medications like barbiturates.
When enabled prior to an EyeDetect test, the examinee will watch a computer screen which slowly changes color from white to black over the period of a few seconds.
The “normal” examinee’s pupils should constrict when the screen is light and dilate when the screen goes dark. If that doesn’t happen, other than the conditions previously mentioned, the likely culprit is that the examinee has used eye drops such as tropicamide, an antimuscarinic drug, to produce short- acting pupil dilation. See a list of similar drugs, visit www.drugs.com. These drugs normally require a prescription and their intended use prior to an EyeDetect test would be considered a countermeasure. Also note, if a person were to use a drug that abnormally dilates or constricts the pupil, the software will note the abnormal pupil size in the test report.
For ‘normal’ examinees, the dilation of the left and right eye closely follow each other, indicating the pupils are dilating in sync. Appropriate pupil reaction to changes in light are constriction (more light) and dilation (less light).
Digit Span Diagnostic
This test is used to measure working memory, mental manipulation, rote memory and learning, attention, and encoding. When enabled prior to an EyeDetect test, the examinee will briefly be presented a sequence of 4, 5, 6, and 7-digit numbers, one at a time. The examinee must recall each number individually after seeing it for a few seconds onscreen by typing the number after it disappears. There are a total of 10 numbers presented during this test.
The “normal” examinee’s pupils should dilate similarly when recalling the number and pupil dilation should slightly increase as the length (complexity) of the number presented increases. Essentially, gradual increases in pupil dilation indicate the task has become more cognitively demanding.
For a ‘normal’ person, dilation of the left and right eye are similar. Appropriate pupil reaction to the memorization of numbers of increasing is pupil dilation, due to the task becoming more cognitively demanding.
Overly excessive eye makeup or extremely dry eyes may affect the test results. The test proctor can put the examinee through a simple calibration process to ensure the eye tracker is able to track the examinee’s eyes.
For examinees with limited reading skills, Converus released a testing protocol in April 2020. It is called the Audio MCT protocol.
There are many conditions in the body that could cause the eyes to dilate in a way that would affect the outcome of the test, including any disorder affecting the hypothalamus and brain stem, the spinal cord, or the autonomic ganglia. Also, multiple system atrophy, Parkinson’s disease, diabetes mellitus, multiple sclerosis, brain or spinal injury, and conditions or diseases that can cause orthostatic hypotension would also affect test results.
EyeDetect has been used to successfully test examinees with Attention Deficit Disorder (ADD), Post-traumatic Stress Disorder (PTSD), Anxiety Disorder, and high functioning Asperger’s syndrome.
EyeDetect has been used to successfully test pregnant examinees or others that have heart arrhythmia or related issues, and asthma or related respiratory diseases.
EyeDetect has been used to successfully test examinees as young as 11 years old.
EyeDetect has been used to successfully test examinees that use anti-depressants and anti-anxiety medications.
EyeDetect is designed to detect lies. If a person confesses before an EyeDetect test, the test is no longer necessary. If that is tested answers the questions truthfully, admitting their guilt, they would not show the same cognitive load changes that a guilty would when trying to hide a lie. Therefore, there is no real need to conduct an EyeDetect test on a person that has confessed.
EyeDetect is designed to detect lies. A guilty person that answers test questions honestly about a crime, for example, will probably not show the same cognitive load changes that a guilty person shows when trying to hide a lie. If a person responds truthfully about using drugs during an EyeDetect test, for example, they may or may not exhibit cognitive change. You can’t really predict if the person will fail or pass a test in this scenario.
While reading a series of questions on a computer screen, EyeDetect measures a person’s response accuracy, response time, pupil diameter, reading behavior and blink rates. This method is consistent with the cognitive workload hypothesis.
- Liars blink significantly less often as they answer questions deceptively, compared to answering truthfully.
- Liars show greater increases in pupil diameter for questions answered deceptively, compared to answering truthfully.
- Liars answer questions faster, make fewer fixations, and spend less time reading questions about a crime they committed than questions about another crime or neutral statements.
Simply put, an increase in cognitive load is associated with remembering a task and is used to distinguish between deceptive and truthful responses. This is more pronounced when liars respond to complex questions. It takes motivation and effort to deceive.
Each test includes pre-test instructions, a practice test, and various sessions of questions. Questions are repeated in a randomized order.
Simply stated, polygraph tests that cover multiple issues (not related to a specific incident) may show reduced accuracy and efficiency. The risk of error increases to the extent that the test includes several separate issues that can be independently answered truthfully or deceptively. Such tests are problematic when the person is truthful about some questions and lying about others.
A field study done for the U.S. Secret Service (Source: Raskin, Kircher, Honts, & Horowitz, 1988) showed that accuracy declines when the examinee answers one or more questions truthfully and one or more deceptively for tests with multiple issues. This data argues against conducting a multi-issue polygraph test, such as drug use and theft and bribery and criminal activity, etc.
The field study mentioned above looked at people that were either truthful or lying to all relevant questions vs. those in which the person was truthful to at least one relevant question and lying about at least one other relevant question. For those subjects, almost half of the test results were inconclusive (49%) and only 74.5% of decisions were correct.
The American Polygraph Association (APA) mentions a study that indicates levels of accuracy as high as 93%. That study was based on polygraph tests done for “event-specific diagnostic examinations used for evidentiary purposes.” In other words, that study mentions data from event-specific tests that are part of an interview, based on evidence; in other words, they involve one event with various, specific issues related to that event.
EyeDetect uses various test formats: (1) Relevant Comparison Test or RCT, which covers two unrelated relevant issues and is used primarily for screening, (2) Multi-Issue Comparison Test or MCT, which covers up to four relevant issues and is used for screening, and (3) Directed Lie Comparison (DLC) test, which is used primary for diagnostic, single issue testing.
Responses to relevant questions are compared by the algorithm to responses about comparison questions.
A polygraph exam that attempts to determine behavior on multiple, potentially unrelated issues, is less accurate because in that exploratory polygraph interview, the examinee may be questioned about separate issues for which s/he may be guilty on some issues and not on other issues. In those cases, there are too many potentially unrelated issues being compared.
EyeDetect is 86-88% accurate for screening because of the use of comparison questions related to two similar, but likely unrelated issues. It’s 87% accurate when conducting single-issue tests.
EyeDetect and Security
Dr. Charles Honts of Boise State University is one of the foremost experts on countermeasures used in polygraph exams. He said the following about using countermeasures with polygraph and EyeDetect:
Countermeasures that work against polygraph are designed to invoke autonomic responses over a period of 20 seconds. Countermeasures can potentially be effective in polygraph because there is time for the countermeasures to be expressed during those 20 seconds.
EyeDetect tests present true/false statements every 5-7 seconds. There is a more direct channel to the examinee’s central nervous system. An EyeDetect examinee must be mentally involved to keep from making errors. Rapid questioning appears to keep the examinee from successfully attempting countermeasures. For this reason, I do not currently see any immediate active countermeasure threats to EyeDetect.
The following are EyeDetect test countermeasures that are unsuccessful:
(1) If the examinee closes his/her eyes or squints when responding to questions, the test proctor can observe this countermeasure.
(2) If the examinee responds “False” to a majority of questions, responds randomly, or chooses not to respond to a significant number of questions (assuming this is done to avoid thinking about the responses), the algorithm observes these patterns of response behavior and the examinee will receive a “Not Credible” score on the test.
Each EyeDetect station has a encrypted hard drive which is 256-bit AES encrypted and FIPS 140-2 validated. All test data are stored on the EyeDetect Station and can only be accessed by users that enter the key to unlock the hard drive. Test data are encrypted using a unique key per customer before being transferred to our secure data center.
Once the data are transferred to the data center they are deleted from hard drive of the EyeDetect Station.
The web-based Converus Dashboard is only accessible using two-factor authentication through SSL. Only authorized users can access the dashboard.
To store and process user data collected during testing, Converus uses standalone (non-hosted) servers that are owned by Converus, and not owned by the data center. Access to these servers is controlled by a firewall and incoming web traffic is monitored for threats. All servers are housed in a private, locked rack in a SSAE 16/ISAE 3402 certified data center. Access to the data center floor is controlled by key card and biometric scanners and is monitored 24/7.
To keep personal information private, can EyeDetect track a person's test results without using a name?
Yes. If an organization wishes to protect the identity of an examinee for purposes of reporting testing results, during registration prior to taking a test, the Test Proctor would provide an identifying number rather than a person’s name.
In addition, the Test Proctor can elect to not take a photo of the person being tested. This way, the organization will need to find test results for a person based on the assigned ID number–after the test is taken, saved, and scored.
EyeDetect and Polygraph
EyeDetect is often used in combination with polygraphs and in some case is used to replace polygraph. In reality, EyeDetect is the perfect add-on service for a polygraph examiner. Studies show that the polygraph can be very accurate for event-specific questioning (a specific line of questioning). In similar diagnostic testing, EyeDetect has shown 86-88% accuracy in field tests, which is comparable to a good polygraph exam. However, studies also show that EyeDetect has comparable levels of accuracy compared to polygraph when used for employee pre-screening and periodic evaluations. The published average accuracy for EyeDetect is 86-88% for screening tests and 87% for single-issue (diagnostic) tests.
The polygraph exam typically has two main uses: (1) incident-specific questioning, like the police use in investigations; and (2) screening tests, such as the ones employed by government agencies.
1) In criminal investigations in the U.S., the polygraph is used to determine if statements by suspects about a specific crime are truthful. The polygraph in this case is specific to the incident in question.
There are two types of questions asked. First, examiners will ask “relevant” questions pertaining to the specific incident under investigation, such as, “Did you rob the Quik Mart on June 14, 2014?” Examiners also use “comparative” questions (called probable lie questions), which are used to establish a reaction to intentionally vague or difficult questions, or are questions that are impossible to answer truthfully with an unqualified negative answer. For example, one might ask, “Between the ages of 18 and 28, did you ever lie to someone in authority?”
At the end of the test, the polygraph examiner compares physiological reactions to the various question types. A person who reacts more strongly to relevant questions is considered deceptive. The accuracy of this type of test is influenced by the skills of the examiner.
Under optimal conditions, the accuracy of probable-lie tests in incident-specific criminal investigations is approximately 90%. (Source: American Polygraph Association Ad Hoc Committee on Polygraph Techniques, 2011)
2) Various U.S. government agencies use the polygraph to screen job applicants, employees, sex offenders, and parolees. In contrast to incident-specific criminal investigations, relevant issues are more general, such as: “In the past 90 days, have you used any illegal drugs?”
The generality of relevant questions in screening examinations is desirable because the test covers a wide range of “bad” or target behaviors. However, the general nature of the relevant questions may introduce ambiguity in the mind of the examinee about their guilt (“I haven’t used illegal drugs in past 90 days, but I used them six months ago, and I know that was wrong”). The generality of relevant questions also increases their similarity to comparison questions, which are intentionally vague and broad in scope.
It is expected that reactions to comparison and relevant questions are more similar in magnitude and less diagnostic in screening tests than specific-incident tests, increasing the risk of false positive and false negative decision errors. In such circumstances, the accuracy of polygraph falls in the range of 65 to 85%.
Polygraphs sense measure and record changes in glucocorticoid (hormone) levels, which initiate chemical reactions such as changes in respiration, heart rate and skin conductance (a moisture buildup under skin). Thus, a polygraph measures physiological changes when under the stress of questioning. That questioning is intended to determine whether a person is truthful. For the polygraph, the primary testing premise is that a liar will show stronger emotional reactions to questions about topics for which they are lying.
EyeDetect measures changes in pupil size and eye movements that reflect changes in brain activity while a person reads and responds to a questionnaire. For EyeDetect, the primary testing premise is that a liar will show an increase in cognitive load when questioned about topics for which they are lying.
Any time a human examiner is tasked with administering polygraph exam questions and scoring the results, mistakes can be made, or bias shown. EyeDetect+ automates the polygraph testing process. Test questions are administered by computer and test results are scored by an advanced computer algorithm. Test instructions and questions are standardized to ensure the test is administered efficiently and reliably.
If EyeDetect and polygraph are used together, the probability of a false negative error is greatly reduced. A false negative results means a liar was categorized as truthful.
EyeDetect primarily measures cognitive processes and the polygraph primarily measures emotional responses. As such, the two tests would be relatively independent and would provide complementary information about a person’s deceptive status.
In the case of liars, both tests aim to keep false negatives at a minimum. When used in combination, EyeDetect and the polygraph can achieve accuracy rates of roughly 97%
To quickly calculate that figure, take the product of the probabilities of false negative errors for the two tests. For example, if the probability of a false negative error is 17% for EyeDetect and 20% for polygraph, the joint probability that a deceptive applicant would pass both tests would be .17 X .20 = .034 or 3.4%. That’s 96.6% accurate.
Combining EyeDetect and polygraph achieves an outcome confidence of 97-99% when used successively. What happens when both are combined into one EyeDetect+ test?
Outcome confidence increases when two independent tests agree. To be independent means the tests must measure different physiological changes. If a polygraph exam is administered by one person one day and an EyeDetect test is administered on the same test topics another day by another person in a different setting, the outcomes will be largely independent and outcome confidence would increase, assuming the tests agree.
Administration of an automated polygraph (both solutions combined) produces results that are more highly correlated (less independent). Thus, outcome confidence is not likely to increase as much. Having said that, the mean accuracy of EyeDetect+ tests is higher than EyeDetect.
One of the most uncomfortable (invasive) components of a polygraph exam is the blood pressure cuff. It is used to measure and record blood pressure changes to assist in rendering a decision on the examinee’s truthfulness. Research shows there is a correlation between blood pressure changes and deception.
The duration of a polygraph exam is affected by the blood pressure cuff (cardiograph) since it must be deflated about every five minutes to restore circulation to the examinee’s arm. A typical polygraph examination lasts 90 minutes or more. If the cuff is not deflated, examinees can become distracted by the pain of the pressure, or tingling of the fingers or, in some cases, broken blood vessels. The examiner must allow the examinee to rest during a polygraph exam to alleviate that discomfort.
EyeDetect+ uses two sensors attached to the wrists to and a photoelectric plethysmograph attached to one finger to calculate blood pressure. There is relatively no discomfort felt by an examinee with these three sensors.
Yes, a pre-test interview can be conducted. The pre-test interview should not transition into an interrogation because the examinee may become overly sensitized and that can affect the test result. This is a reliable way to collect data. Note: the examiner needs to be a skilled interviewer to effectively conduct a pre-test interview.
The test administrator or examiner should conduct a pre-test interview with the examinee to get an informed consent and authorization for release, to discuss the examinee’s suitability, to review any Interview Route Maps (if applicable), to explain how the testing equipment works, to discuss the testing procedure, and to discuss how test results are given.
A post-test interview is also recommended for examinees that fail the test. Using investigative interviewing techniques, the examiner can explore with the examinee the reason for test failure. This has been shown scientifically to improve information gain and, unless the behavior discussed would disqualify the applicant, it could assist the examiner in the creation of a break-down test to ensure credibility if a follow-on test is administered.
That data from the traditional polygraph sensors are visually available to view and score manually, if desired. Examiners must decide which scoring model to use. For example, polygraph examiners should be familiar with the four presentations of three relevant and three Directed Lie Comparison questions.
Ocular motor measurements shown onscreen cannot be scored by an examiner. That scoring can only be done by a sophisticated algorithm because there is too much data gathered, too quickly. For this reason, Converus recommends relying on the algorithm for test scoring. The computerized scoring method has 100% reliability.
When a liar comes up with a cover story, there’s an increase in brain activity (cognitive load). If someone is able to create a cover story without increasing brain activity, that person will appear less deceptive. Pupils react involuntarily to an increase in cognitive load and for that reason, EyeDetect has shown a superior level of accuracy compared to all other lie detection solutions on the market.
Although the EPPA law specifically mentions polygraph, the law has been applied in practice more broadly to any lie detectors. EPPA is concerned with protecting a person’s right to privacy in employment. So, any lie detector is prohibited. However, lie detectors can be used for screening or evaluating federal, state, or local government employees. This includes law enforcement, other public safety personnel, and national security agencies.
EyeDetect+ is a solution that meets the functional definition of polygraph and would comply with the law in any U.S. state.
The absence of probable-lie comparison questions in an EyeDetect test eliminates concerns about any overlap that might occur between “relevant” and “comparison” questions (see “How is the polygraph typically used? What is the average accuracy for those uses?” above).
Reactions to two sets of “relevant” questions are compared and each relevant issue serves as a control for the other issue.
An EyeDetect test is almost completely automated and is administered by a computer. Therefore, the accuracy of the test does not depend on the interview skills of the examiner or their ability to interpret physiological recordings. In contrast to a polygraph, the examinee for the EyeDetect test does not have to attempt to appear truthful to an examiner.
EyeDetect tests can be developed for any language, allowing testing in the native tongue of an examinee. This eliminates the need for a translator and prevents language misunderstandings.
An EyeDetect test is not intrusive like a polygraph. No sensors are attached to the body. A remote camera records eye behavior during the test.
An EyeDetect tests takes from 15 to 30 minutes depending on the format used, and results are generated in less than 5 minutes. In contrast, a polygraph may take 90 minutes or more. An organization can conduct up to six EyeDetect tests in the time it takes to conduct one polygraph test.
Lying, Lies and Liars
A University of Massachusetts study revealed that 60% of people self-report they could not carry on a 10-minute conversation without lying at least once. British research found that men lie twice as much as women. (Source: http://www.today.com/health/how-one-lie-can-ruin-your-whole-day-1D80224805#)
In reality, the more prone to lying, the more a person fabricates details and events to create a cover story. Lies breed lies. Research indicates the accompanying stress can be harmful and even exhausting. The longer a person attempts to “keep a cover story straight,” the more stress and strain is felt.
That discomfort may lead to more serious side effects in the future. A Columbia University study shows stressed-out people were 27% more likely to have heart attacks compared to those who worried less.
Stanford researchers conducted a study to measure the effect of lying on a group of participants who said dishonest acts made physical tasks, such as working out or helping someone move, feel more taxing. In addition, deceptive participants suggested that hills seemed steeper and distances seemed farther.
Deceptive thoughts may activate parts of your brain tied to perception and vision in the same way as when you are physically weighed down. This can lead to physical overexertion, exhaustion, and stress. Therefore, the heavier the lie you carry, the heavier those bench presses may feel.
Notre Dame researchers found that subjects that were told to explicitly tell the truth reported lying less frequently and reported having improved relationships, better sleep, and less tension, as well as fewer headaches and sore throats.
There are many methods to be deceptive. At the heart of these methods is the intention to be deceptive. Some lie to be protective – lie to guard the liar from a perceived danger. Some, to be heroic – lie to protect others from danger. Others lie in a playful manner – lie to enhance a story. For others, it’s about ego – lie to help the liar prevent embarrassment. As things get darker, some lie for gainful purposes – lie to benefit the liar or to be malicious – lie to hurt others.
Other Lie Detectors
Research shows that an electroencephalogram (EEG) and the fMRI may achieve results of 87% accuracy. However, both test are intrusive (the examinee is connected extensively to medical instruments or is inserted into a large tube). Both methods are costly, require expensive equipment and extensive training to operate. For these reasons, neither is a viable solution.
How effective is intuition as a lie detector? Can you tell if someone is lying when having a conversation?
Studies say that human lie detectors have an accuracy rate of 54% at spotting a liar. (Source: Bond & DePaulo, 2006) If that’s true, you’ll get the same results from chance, or in other words, from the flip of a coin.
Behaviors such as gaze aversion, touching the body or face, or covering the eyes or mouth while speaking have not been found to be reliable indicators for deception.
Aptitude tests determine if a person is able to do the job. In other words, can the candidate perform a job function? Predicting if someone will do the job is a challenge.
Predicting if someone will lie, cheat, or steal is also a challenge. The premise behind EyeDetect is that it measures reactions to recent or past behavior. An employer can determine how to use that information to take action with an employee.
Personality tests try to determine if there is a job fit from a behavioral perspective. The challenge with a personality test is that there are no right or wrong answers. The test will assess a person’s dominance, altruism, neuroticism, egotism, psychopathy, introversion, etc. or other items.
Some personality tests try to assess a person’s willingness to pretend to be good. Employment personality tests try to determine a person’s interaction style and behavioral tendencies. They attempt to assess aspects of personality that remain relatively stable throughout a lifetime. They also attempt to predict future behavior.
Integrity tests assess the likelihood an employee will engage in dishonest behavior. This is an attempt to predict future behavior. An “overt” integrity test discusses past criminal behavior and attitudes about honesty, drug use, theft and counterproductive behavior. If a person is completely honest, this test can be very valuable. Deceptive individuals may not be forthright in their responses.
One notable study entitled “The Use of Integrity Tests for Pre-employment Screening” discusses the validity of integrity tests. The study was published by the Office of Technology Assessment (OTA) of the U.S. Congress.
Some points of interest follow:
Studies on Workplace Theft
The results from 5 studies on workplace theft showed that integrity tests misclassified liars as honest between slightly less than 1% to 6% of the time. The tests also misclassified truth tellers as liars from 73 to 97% of the time. In summary, workers were misclassified between 18% to 64% of the time. (pp 10-11)
Studies on Counterproductive Behavior at Work
The results from 3 studies on counterproductive behavior showed that integrity tests misclassified counterproductive persons as productive between 18 to 29% of the time. Two of these studies also misclassified productive people as counterproductive from 22 to 29% of the time. (p 11)
Honest People Fail
Other research showed that between 30% and 60% of all applicants will “fail” an integrity test (categorized as dishonest). There could be an important number of honest people that are turned away. (p. 12)
This test is based on the premise that muscles in the voice box tighten or loosen when lying, which changes the sound of the voice. The small, involuntary frequency modulations in the voice when under stress (i.e., lying) are measured.
Studies show these tests operates at about a chance level or slightly higher (50-65% accurate). That means it would be similar to a flip of a coin. Source: Journal of Forensic Sciences, 53(1), 183-193, Hollien and Harnsberger (2008).
IdentityDetect is a quick and simple web-based test or mobile app that can quickly verify a person’s identity. IdentityDetect measures an applicant’s responses, applies a scoring algorithm, and uses machine learning to determine a credibility score for the person. Results are available immediately, allowing the process to continue or to be flagged for further review.
Lab studies conducted by researchers at the University of Padua, Italy and confirmed by field studies run by Converus, Inc. confirm the accuracy of IdentityDetect is 90%.
Any industry concerned with validating the identity of its customers or employees will benefit greatly from using IdentityDetect. There is great initial interest from financial services and immigration, but also we see application for IdentityDetect in pre-employment screening, real estate leasing, vacation rentals and relationship sites.
IdentityDetect uses different evaluation models, depending on the specific business requirements. Generally, the evaluation is self-contained, performed in a web browser or a mobile app, and requires the user to complete a form or answer some Yes/No questions. Instructions are included with the test, when necessary.
Evaluations are processed immediately, with results available usually within seconds. The user being evaluated is typically not shown the results.
Yes. IdentityDetect offers an SDK for custom integrations. Using a REST interface, requests and responses are all handled via HTTPS using JSON, allowing organizations to integrate with the programing language of their choice. For mobile application development, the SDK includes pre-built libraries to streamline the integration process.
Yes. IdentityDetect is designed to be integrated within existing web and mobile applications. Customers can do simple branding customizations of the evaluation portal or deep integrations within applications.
EyeDetect measures changes in the eyes and other behaviors. IdentityDetect measures changes in the motor nervous system. EyeDetect requires a special high-definition, infrared eye-tracking camera and custom software. IdentityDetect requires a browser or app and internet access. EyeDetect has numerous peer-reviewed studies on the technology. IdentityDetect is newer and has fewer studies. EyeDetect can test for a number of issues. IdentityDetect focuses on identity verification. Both have a place in credibility assessment and can be used together.
Since IdentityDetect is ultimately determining if a person is lying about his or her identity, we believe IdentityDetect does not fall under EPPA. Although the EPPA law specifically mentions polygraph, the law has been applied in practice more broadly to the use of any lie detection solution. At the heart of the law is the concept of protecting a person’s right to privacy in employment. Thus, any lie detector would be prohibited. However, lie detection solutions can be used today for screening or evaluating federal, state or local government employees, including law enforcement. Outside of employment, IdentityDetect can be used to validate anyone’s identity.
Converus (“with truth”) provides scientifically validated credibility assessment technologies that help protect countries, corporations and communities from corruption, crime and threats.