Abstract: A newly developed system might quickly assist to foretell the place poachers are more likely to strike in wildlife parks. USC pc scientist speaks at a White Home-sponsored workshop on expertise and social good. Poachers hunt tigers with traps and weapons. That prime-tech software is in improvement due to USC laptop scientist Milind Tambe, the Helen N. and Emmett H. Jones Professor in Engineering on the USC Viterbi College of Engineering. Since 2013, he's been working with worldwide businesses to check software program he hopes will sooner or later predict the place poachers are prone to strike inside wildlife parks.
In all of these problems, we have limited be done; yet these are large-scale interdisciplinary research security resources which prevent full security coverage challenges that call upon multiagent researchers to work at all times; instead, limited security resources must be deployed with researchers in other disciplines, be "on the ground" intelligently taking into account differences in priorities with domain experts, and examine real-world constraints of targets requiring security coverage, the responses of and challenges that cannot be abstracted away. Together as the adversaries to the security posture and potential uncertainty an international community of multiagent researchers, we over the types, capabilities, knowledge and priorities can accomplish more! of adversaries faced.
In all of these problems, we have limited with researchers in other disciplines, be "on the ground" security resources which prevent full security coverage with domain experts, and examine real-world constraints at all times; instead, limited security resources must be deployed and challenges that cannot be abstracted away. Together as intelligently taking into account differences in priorities an international community of multiagent researchers, we of targets requiring security coverage, the responses of can accomplish more! the adversaries to the security posture and potential uncertainty over the types, capabilities, knowledge and priorities
An, Bo (University of Southern California) | Jain, Manish (University of Southern California) | Tambe, Milind (University of Southern California) | Kiekintveld, Christopher (University of Texas, El Paso)
Stackelberg games have been widely used to model patrolling or monitoring problems in security. In a Stackelberg security game, the defender commits to a strategy and the adversary makes its decision with knowledge of the leader's commitment. Algorithms for computing the defender's optimal strategy are used in deployed decision-support tools in use by the Los Angeles International Airport (LAX), the Federal Air Marshals Service, and the Transportation Security Administration (TSA). Those algorithms take into account various resource usage constraints defined by human users. However, those constraints may lead to poor (even infeasible) solutions due to users' insufficient information and bounded rationality. A mixed-initiative approach, in which human users and software assistants (agents) collaborate to make security decisions, is needed. Efficient human-agent interaction process leads to models with higher overall solution quality. This paper preliminarily analyzes the needs and challenges for such a mixed-initiative approach.
The problem of how to defend a country changes when your attacker isn't acting rationally. Terrorists put their causes above their home country and don't necessarily fear death or retaliation. So shortly after 9/11, Milind Tambe, a professor of computer science and engineering at USC, proposed a radical new style of protection: Why not use artificial intelligence to make your own targets harder to attack? By matching predictive algorithms with machine learning and some massive processing power, you could create a computer program capable of figuring out how to deploy limited security forces around sensitive places most effectively. The trick would be for those schedules or formations to remain unpredictable.