Events Calendar

PhD Defense - Yundi Qian

Title: Handling Attacker's Preference in Security Domains: Robust and Learning Approaches

PhD Candidate: Yundi Qian

Location: VKC 252
Time: 2pm, April 14th, Thursday

Committee members:
Milind Tambe
Aram Galstyan
Jonathan Gratch
Maged Dessouky (Outside Member)
Yilmaz Kocer (Outside Member)


Abstract:
Stackelberg security games (SSGs) are now established as a powerful tool in security domains. In order to compute the optimal strategy for the defender in SSG model, the defender needs to know the attacker's preferences over targets so that she can predict how the attacker would react under a certain defender strategy. Uncertainty over attacker preferences may cause the defender to suffer significant losses. Motivated by that, my thesis focuses on addressing uncertainty in attacker preferences using robust and learning approaches.

In security domains with one-shot attack, e.g., counter-terrorism domains, the defender is interested in robust approaches that can provide performance guarantee in the worst case. The first part of my thesis focuses on handling attacker's preference uncertainty with robust approaches in these domains. My work considers a new dimension of preference uncertainty that has not been taken into account in previous literatures: the risk preference uncertainty of the attacker, and propose an algorithm to efficiently compute defender's robust strategy against uncertain risk-aware attackers.

In security domains with repeated attacks, e.g., green security domain of protecting natural resources, the attacker ``attacks'' (illegally extracts natural resources) frequently, so it is possible for the defender to learn attacker's preference from their previous actions and then to use this information to better plan her strategy. The second part of my thesis focuses on learning attacker's preferences in these domains. My thesis models the preferences from two different perspectives: (i) the preference is modeled as payoff and the defender learns the payoffs from attackers' previous actions; (ii) the preference is modeled as a markovian process and the defender learns the markovian process from attackers' previous actions.

Location: Von Kleinsmid Center For International & Public Affairs (VKC) - 252

Audiences: Everyone Is Invited

Contact: Lizsl De Leon