REVERSE ENGINEERING HUMAN MENTAL STATE

Speaker: David Skillicorn, Queen’s University – Canada Seminar Date: Tuesday June 27 12:00pm Brief abstract:Often, especially in adversarial settings, we don’t have direct access to persons of interest. Fortunately, humans leak a great deal of their mental state and behaviour through the language they use and the relationships they create. These data can be captured and analysed computationally, allowing inferences to be made about the individuals and groups concerned. Properties detectable from language include strategic intent (deception, jihadist intensity, propaganda) and affective state (personality) as well as how these are changing, giving insight into internal group dynamics and reactions to the external world. The social networks constructed by bad actors are qualitatively different from ordinary ones. Social network analysis can be used to understand the structure of bad actor networks, and also to identify leaders or unusual members. In the online world, bad actors can easily hide; but this kind of analysis makes it possible to learn about them anyway, and so develop defences. I will illustrate with real-world data. Short Bio: David Skillicorn is a Professor in the School of Computing at Queen’s University (on sabbatical at UTS, Sydney). His undergraduate degree is from the University of Sydney and his Ph.D. from the University of Manitoba. He has published extensively in the area of adversarial data analytics, including his recent books “Social Networks with Rich Edge Semantics” and “Knowledge Discovery for Counterterrorism and Law Enforcement”. He has also been involved in interdisciplinary research on radicalisation, terrorism, and financial fraud. He consults for the intelligence and security arms of government in several countries, and appears frequently in the media to comment on issues such as cybersecurity and terrorism.