Deception Detection via Interviewer Biometrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current deception detection methods, such as polygraph tests, face challenges in accuracy and create an artificial environment that can affect subject behavior, leading to a need for improved techniques that do not require biometric monitoring.
Innovation Solution
A method that predicts trustworthiness in real-time using a pre-established schema with prompts and responses, leveraging reaction times, conscious and subconscious impressions, and biometric data from the interviewer, without requiring biometric sensors on the subject, and utilizing machine learning techniques to analyze data from both the subject and interviewer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If biometric sensors are placed on the subject for polygraph testing, then deception detection capability is improved, but the artificial environment affects subject behavior and creates reluctance to be interviewed
Solution Approach 1:
The patent inverts the traditional polygraph approach by placing biometric sensors on the interviewer instead of the subject. The system measures the interviewer's physiological responses (heart rate, skin conductance, respiratory rate) during the interview, using these as indicators of the interviewer's subconscious reactions to the subject's truthfulness. This inversion eliminates the need to attach sensors to the subject while still providing deception detection capability through the interviewer's physiological data.
Solution Approach 2:
The interviewer serves as an intermediary between the subject and the detection system. Rather than directly measuring the subject's physiological state, the system measures the interviewer's physiological responses to the subject's behavior. The interviewer's subconscious reactions act as a mediator that translates the subject's deceptive or truthful behavior into measurable physiological signals.
2Reliability
If polygraph testing is used for deception detection, then some level of deception identification is achieved, but the quantitative accuracy is debated and results are not admissible in court
Solution Approach 1:
The system incorporates multiple feedback mechanisms including the interviewer's conscious impressions, subconscious physiological responses, and subject behavioral data. These feedback streams are integrated and analyzed together to produce a comprehensive trustworthiness assessment. The feedback loop allows the system to continuously refine its predictions based on multiple independent indicators, improving measurement precision and reliability.
Solution Approach 2:
The patent combines multiple types of data (interviewer biometric data, interviewer reaction times, conscious impressions, and subject response data) into a composite assessment model. This composite approach integrates diverse information sources to create a more robust and accurate deception detection system, similar to how composite materials combine different substances to achieve superior properties.
3Loss of information
If traditional polygraph methods are used, then biometric monitoring provides deception indicators, but the requirement creates an artificial environment that heightens subject reluctance
Solution Approach 1:
The patent extracts the biometric monitoring function from the subject and relocates it to the interviewer. By taking out the sensors from the subject's body and placing them on the interviewer, the system eliminates the artificial and intrusive nature of subject monitoring while preserving the capability to collect relevant biometric data for deception detection.
Data Source
AI summary
A method for predicting subject trustworthiness includes using at least one classifier to predict truthfulness of subject responses to prompts during a local or remote interview, based on subject responses and response times, as well as interviewer impressions and response times, and, in embodiments, also biometric measurements of the interviewer. Data from the subject interview is normalized and analyzed relative to an experience database previously created using data obtained from test subjects. Classifier prediction algorithms incorporate assumptions that subject response times are indicators of truthfulness, that subjects will tend to be consistently truthful or deceitful, and that conscious and subconscious impressions of the interviewer are predictive of subject trustworthiness. Data regarding interviewer impressions can be derived from interviewer response times, interviewer questionnaire answers, and/or interviewer biometric data. Appropriate actions based on trustworthiness predictions can include denial of security clearance or further investigation relevant to the subject.