Deception-detection and machine intelligence in practical Turing tests

Deception-detection is the crux of Turing’s experiment to examine machine thinking conveyed through a capacity to respond with sustained and satisfactory answers to unrestricted questions put by a human interrogator. However, in 60 years to the month since the publication of Computing Machinery and Intelligence little agreement exists for a canonical format for Turing’s textual game of imitation, deception and machine intelligence. This research raises from the trapped mine of philosophical claims, counter-claims and rebuttals Turing’s own distinct five minutes question-answer imitation game, which he envisioned practicalised in two different ways: a) A two-participant, interrogator-witness viva voce, b) A three-participant, comparison of a machine with a human both questioned simultaneously by a human interrogator. Using Loebner’s 18th Prize for Artificial Intelligence contest, and Colby et al.’s 1972 transcript analysis paradigm, this research practicalised Turing’s imitation game with over 400 human participants and 13 machines across three original experiments. Results show that, at the current state of technology, a deception rate of 8.33% was achieved by machines in 60 human-machine simultaneous comparison tests. Results also show more than 1 in 3 Reviewers succumbed to hidden interlocutor misidentification after reading transcripts from experiment 2. Deception-detection is essential to uncover the increasing number of malfeasant programmes, such as CyberLover, developed to steal identity and financially defraud users in chatrooms across the Internet. Practicalising Turing’s two tests can assist in understanding natural dialogue and mitigate the risk from cybercrime.

Intuition and its component parts in the heuristic processing of deception detection: Hunch, *evidence, and reliance on intuitive efficacy

Rated trust in intuitive efficacy (measured as trust, belief, use, accuracy and weighting of intuition) was investigated as a predictor of self-designated use of intuitive (hunch and hunch plus evidential belief) vs. deliberative (evidential belief and evidential belief plus hunch) deception detection judgments and actual accuracy. Twenty-nine student participants were filmed as they made true and deceptive statements about their everyday activities on a given evening (last Friday night), and college students (N=238) judged 20 (10=true, 10=deceptive) of these filmed statements as truthful or deceptive. Participants provided ratings of reliance on hunches vs. evidential belief, confidence in film judgments, intuitive efficacy, accuracy in deception detection, reliance on cues to deception, and experiences with intuition. Generalized estimated equation modeling using binary logistics demonstrated accuracy in identifying true vs. deceptive statements was predicted by film number, hunch-evidence ratings, weighting of intuition, and total cues cited. Weighting of intuition was predictive of accuracy across participants, with higher weighting predictive of higher accuracy in general. Participants who cited evidential belief plus hunch and moderate to high weighting incorrectly reversed their true vs. deceptive judgments. Accuracy for true statements was higher for hunches and hunch plus evidential belief, whereas accuracy for deceptive statements was higher for evidential belief Accuracy for participants who relied on evidential belief plus hunch was at chance. Subjective experiences underlying judgments differed by participant and type of film viewed (true vs. deceptive) and were predicted by hunch-evidence ratings, trust, use, intuitive accuracy, and total cues cited. Trust predicted increases in judging films to be true, whereas use and accuracy predicted increases in judging films as deceptive; none were predictive of accuracy. Increased number of cues cited predicted judgments of deception, whereas decreased number of cues cited predicted truth. The study concluded that participants have the capacity to self-define their judgments as subjectively vs. deliberately based, provide subjective assessments of the influence of intuitive vs. objective information on their judgments, and can apply this self-knowledge, through effective weighting of intuition vs. other types of information, in making accurate judgments of true and deceptive everyday statements.

The effect of cognitive load on deception

The current study applied classic cognitive capacity models to examine the effect of cognitive load on deception. The study also examined whether the manipulation of cognitive load would result in the magnification of differences between liars and truth-tellers. In the first study, 87 participants engaged in videotaped interviews while being either deceptive or truthful about a target event. Some participants engaged in a concurrent secondary task while being interviewed. Performance on the secondary task was measured. As expected, truth tellers performed better on secondary task items than liars as evidenced by higher accuracy rates. These results confirm the long held assumption that being deceptive is more cognitively demanding than being truthful. In the second part of the study, the videotaped interviews of both liars and truth-tellers were shown to 69 observers. After watching the interviews, observers were asked to make a veracity judgment for each participant. Observers made more accurate veracity judgments when viewing participants who engaged in a concurrent secondary task than when viewing those who did not. Observers also indicated that participants who engaged in a concurrent secondary task appeared to think harder than participants who did not. This study provides evidence that engaging in deception is more cognitively demanding than telling the truth. As hypothesized, having participants engage in a concurrent secondary task led to the magnification of differences between liars and truth tellers. This magnification of differences led to more accurate veracity rates in a second group of observers. The implications for deception detection are discussed.

The Effect of Cognitive Load on Deception

The current study applied classic cognitive capacity models to examine the effect of cognitive load on deception. The study also examined whether the manipulation of cognitive load would result in the magnification of differences between liars and truth-tellers. In the first study, 87 participants engaged in videotaped interviews while being either deceptive or truthful about a target event. Some participants engaged in a concurrent secondary task while being interviewed. Performance on the secondary task was measured. As expected, truth tellers performed better on secondary task items than liars as evidenced by higher accuracy rates. These results confirm the long held assumption that being deceptive is more cognitively demanding than being truthful. In the second part of the study, the videotaped interviews of both liars and truth-tellers were shown to 69 observers. After watching the interviews, observers were asked to make a veracity judgment for each participant. Observers made more accurate veracity judgments when viewing participants who engaged in a concurrent secondary task than when viewing those who did not. Observers also indicated that participants who engaged in a concurrent secondary task appeared to think harder than participants who did not. This study provides evidence that engaging in deception is more cognitively demanding than telling the truth. As hypothesized, having participants engage in a concurrent secondary task led to the magnification of differences between liars and truth tellers. This magnification of differences led to more accurate veracity rates in a second group of observers. The implications for deception detection are discussed.

Evaluación del testimonio: errores de memoria y mentiras

[ES]Este Trabajo de Fin de Grado (TFG) consiste en una revisión bibliográfica sobre los errores de memoria y la mentira en el testimonio. Para ello, por un lado, se explicarán los tipos de errores de memoria que se pueden dar en el testimonio, así como los factores que influyen en la exactitud de la memoria de los testigos, víctimas y/o agresores, y por otro lado, las mentiras que se pueden contar junto con su posible detección mediante indicadores verbales y no verbales. Respecto a la parte empírica, se recogerán y analizarán los resultados obtenidos gracias a diferentes estudios recogidos en un meta-análisis sobre la capacidad que tienen los policías para detectar la mentira en un testimonio.

Opening up a can of worms: how do decision-makers decide when witnesses are telling the truth?

Correctly determining witness credibility is integral to a fair trial. Assessments of credibility made by the triers of fact are made, amongst other things, by reference to behavioural stereotypes that are commonly thought to be associated with lying and truth-telling. These stereotypes are worthless but pervasive. In this study, potential jurors were given information such as would be given by way of judicial direction and/or expert testimony on those behavioural indicia that are useful in detecting deception. Major changes in perceptions of what does and does not work were found. This has significant implications for the conduct of criminal trials. Recommendations are presented which, it is argued, can be of real, practical, assistance in enabling decision-makers to assess the credibility of witnesses. © 2013 The Australian and New Zealand Association of Psychiatry, Psychology and Law.

DIANA: análisis del discurso para la comprensión del conocimiento

DIANA es un proyecto coordinado en el que participan el grupo de Ingeniería del Lenguaje Natural y Reconocimiento de Formas (ELiRF) de la Universitat Politècnica de València y el grupo Centre de Llenguatge i Computació (CLiC) de la Universitat de Barcelona. Se trata de un proyecto del programa de I+D (TIN2012-38603) financiado por el Ministerio de Economía y Competitividad. Paolo Rosso coordina el proyecto DIANA y lidera el subproyecto DIANA-Applications y M. Antònia Martí lidera el subproyecto DIANA-Constructions.

Exoneration or Observation? Examining a Novel Difference Between Liars and Truth Tellers

Individual cues to deception are subtle and often missed by lay people and law enforcement alike. Linguistic statement analysis remains a potentially useful way of overcoming individual diagnostic limitations (e.g. Criteria based Content Analysis; Steller & Köhnken, 1989; Reality monitoring; Johnson & Raye, 1981; Scientific Content Analysis; Sapir, 1996). Unfortunately many of these procedures are time-consuming, require in-depth training, as well as lack empirical support and/or external validity. The current dissertation develops a novel approach to statement veracity analysis that is simple to learn, easy to administer, theoretically sound, and empirically validated. Two strategies were proposed for detecting differences between liars' and truth-tellers' statements. Liars were hypothesized to strategically write statements with the goal of self-exoneration. Liars' statements were predicted to contain more first person pronouns and fewer third person pronouns. Truth-tellers were hypothesized to be motivated toward being informative and thus produce statements with fewer first person pronouns and more third person pronouns. Three studies were conducted to test this hypothesis. The first study explored the verbal patterns of exoneration and informativeness focused statements. The second study used a traditional theft paradigm to examine these verbal patterns in guilty liars and innocent truth tellers. In the third study to better match the context of a criminal investigation a cheating paradigm was used in which spontaneous lying was induced and written statements were taken. Support for the first person pronoun hypothesis was found. Limited support was found for the third person pronoun hypothesis. Results, implications, and future directions for the current research are discussed.

The Illinois Detection of Deception Examiners Act.

Description based on: 1985; title from cover.

Untangling a Web of Lies: Exploring Automated Detection of Deception in Computer-Mediated Communication

Safeguarding organizations against opportunism and severe deception in computer-mediated communication (CMC) presents a major challenge to CIOs and IT managers. New insights into linguistic cues of deception derive from the speech acts innate to CMC. Applying automated text analysis to archival email exchanges in a CMC system as part of a reward program, we assess the ability of word use (micro-level), message development (macro-level), and intertextual exchange cues (meta-level) to detect severe deception by business partners. We empirically assess the predictive ability of our framework using an ordinal multilevel regression model. Results indicate that deceivers minimize the use of referencing and self-deprecation but include more superfluous descriptions and flattery. Deceitful channel partners also over structure their arguments and rapidly mimic the linguistic style of the account manager across dyadic e-mail exchanges. Thanks to its diagnostic value, the proposed framework can support firms’ decision-making and guide compliance monitoring system development.

A method of fraud & intrusion detection for e-payment systems in mobile

The need for paying with mobile devices has urged the development of payment systems for mobile electronic commerce. In this paper we have considered two important abuses in electronic payments systems for detection. The fraud, which is an intentional deception accomplished to secure an unfair gain, and an intrusion which are any set of actions that attempt to compromise the integrity, confidentiality or availability of a resource. Most of the available fraud and intrusion detection systems for e-payments are specific to the systems where they have been incorporated. This paper proposes a generic model called as Activity-Event-Symptoms(AES) model for detecting fraud and intrusion attacks which appears during payment process in the mobile commerce environment. The AES model is designed to identify the symptoms of fraud and intrusions by observing various events/transactions occurs during mobile commerce activity. The symptoms identification is followed by computing the suspicion factors for event attributes, and the certainty factor for a fraud and intrusion is generated using these suspicion factors. We have tested the proposed system by conducting various case studies, on the in-house established mobile commerce environment over wired and wire-less networks test bed.

Detecting deception: Identifying differences in liars' and truth tellers' verbal strategies

Deception research has traditionally focused on three methods of identifying liars and truth tellers: observing non-verbal or behavioral cues, analyzing verbal cues, and monitoring changes in physiological arousal during polygraph tests. Research shows that observers are often incapable of discriminating between liars and truth tellers with better than chance accuracy when they use these methods. One possible explanation for observers' poor performance is that they are not properly applying existing lie detection methods. An alternative explanation is that the cues on which these methods — and observers' judgments — are based do not reliably discriminate between liars and truth tellers. It may be possible to identify more reliable cues, and potentially improve observers' ability to discriminate, by developing a better understanding of how liars and truth tellers try to tell a convincing story. ^ This research examined (a) the verbal strategies used by truthful and deceptive individuals during interviews concerning an assigned activity, and (b) observers' ability to discriminate between them based on their verbal strategies. In Experiment I, pre-interview instructions manipulated participants' expectations regarding verifiability; each participant was led to believe that the interviewer could check some types of details, but not others, before deciding whether the participant was being truthful or deceptive. Interviews were then transcribed and scored for quantity and type of information provided. In Experiment II, observers listened to a random sample of the Experiment I interviews and rendered veracity judgments; half of the observers were instructed to judge the interviews according to the verbal strategies used by liars and truth tellers and the other half were uninstructed. ^ Results of Experiment I indicate that liars and truth tellers use different verbal strategies, characterized by a differential amount of detail. Overall, truthful participants provided more information than deceptive participants. This effect was moderated by participants' expectations regarding verifiability such that truthful participants provided more information only with regard to verifiable details. Results of Experiment II indicate that observers instructed about liars' and truth tellers' verbal strategies identify them with greater accuracy than uninstructed observers. ^