Search

We first discuss certain problems with the classical probabilistic approach for assessing forensic evidence, in particular its inability to distinguish between lack of belief and disbelief, and its inability to model complete ignorance within a given population. We then discuss Shafer belief functions, a generalization of probability distributions, which can deal with both these objections. We use a calculus of belief functions which does not use themuch criticized Dempster rule of combination, but only the very natural Dempster-Shafer conditioning. We then apply this calculus to some classical forensic problems like the various island problems and the problem of parental identification. If we impose no prior knowledge apart from assuming that the culprit or parent belongs to a given population (something which is possible in our setting), then our answers differ from the classical ones when uniform or other priors are imposed. We can actually retrieve the classical answers by imposing the relevant priors, so our set-up can and should be interpreted as a generalization of the classicalmethodology, allowingmore flexibility. We show how our calculus can be used to develop an analogue of Bayes' rule, with belief functions instead of classical probabilities. We also discuss consequences of our theory for legal practice. [ABSTRACT FROM AUTHOR]

It is investigated how implementing the likelihood ratio (LR) framework works out in the case of camera identification based on image-sensor-specific noise patterns. Two typical case scenarios are considered, one with images of low quality andthe other with images of high quality. In both cases, it is possible to obtain statistical distributions having a good fit with the reference data both for ‘matching’ and for ‘non-matching’ comparisons, and LRs are determined. It turns out that if the reference data are well separated, in the case of ‘matching’ images/cameras, the statistical fit of the distribution for ‘non-matches’ is constantly evaluated in a range where there is a lack of reference data. Because of this extrapolation issue, the LRsthat emerge are not reliable. This is not a problem that is unique to camera identification: if the informative value of any forensic comparison is high the problem emerges. An alternative approach is presented which consists of choosing a threshold value separating ‘matches’ from ‘non-matches’ and quantifying the strength of evidence of being larger/smaller than this value. If sample sizes of reference data increase LR results will increase as well, and it is shown that this approach is stable. [ABSTRACT FROM PUBLISHER]

These are perilous times in which our security is under continual threat by persons and organizations around the world and at home. Information supplied to us by human sources concerning the capabilities and intentions of these persons and organizations is crucial to our ability to recognize and prevent these threatening actions. We have all seen the many news accounts of our need for more and better HUMINT (human intelligence). But a major issue is the following: when we obtain an item of HUMINT, to what extent can we believe it? Our ability to make these assessments involves determining the competence and credibility of the human source providing this item. These assessments are very difficult and the persons making them need all the help they can get. Fortunately, much assistance comes from the fields of law and probability. This paper provides an account of how we are now exploiting the very rich legacy of experience and scholarship accumulated in the field of law over the past 500 years or so regarding questions to ask about the competence and credibility of witnesses. For quite some time, we have been attempting to bring valuable insights from the field of law concerning various evidential and inferential matters to the attention of persons in the intelligence community. On this occasion, we will describe a computer-assisted system called MACE (method for assessing the credibility of evidence), which we are developing to exploit what we have learned from law regarding assessments of the competence and credibility of sources of HUMINT. This system is designed to assist in addressing the question: to what extent can we believe this particular item of HUMINT that has just been supplied to us by a human source? MACE employs two different, but entirely complementary, probability systems to help us answer this question. Baconian probability methods help us answer the question: how much evidence do we have about this human source and how completely does it answer questions about the source's competence and credibility? Bayesian probability methods allow us to determine how strong is the evidence we do have about this particular human source, and it also provides an assessment of the posterior odds favouring the extent to which we can believe or disbelieve what this source is telling us. [ABSTRACT FROM AUTHOR]