DCAI Conference 2019

V.S. Subrahmanian is The Dartmouth College Distinguished Professor in Cybersecurity, Technology, and Society at Dartmouth Collage with tenure in the Computer Science Department. Cybersecurity, Technology, and Society (ISTS) at Dartmouth Collage. Prior to joining Dartmouth, he was a tenured Professor in the [University of Maryland's Computer Science Department] (www.cs.umd.edu). He served a 6.5 year stint as Director of the University of Maryland Institute for Advanced Computer Studies where he co-founded the Lab for Computational Cultural Dynamics and founded the Center for Digital InternationalGovernment. His work stands squarely at the intersection of big data analytics for increased security, policy, and business needs. Prof. Subrahmanian has been an invited speaker at the United Nations, Capitol Hill, the Mumbai Stock Exchange, and numerous other prestigious forums.

There are numerous types of malicious networks in the real world that "hide" within larger networks. For instance, sub-networks of influence bots on Twitter "hide" within the overall Twitter network. Sockpuppet networks (sets of usually connected accounts operated by one individual) often disrupt meaningful conversation in online news and other discussion forums. Terrorist networks hide within networks composed of members of a general population. Disrupting such networks involves two parts: developing methods to detection nodes in such networks that are involved in malicious behavior, and identifying methods to "reshape" the malicious subnetworks. I will use data-driven case studies from online review fraud, online discussion forums, and Twitter to discuss the first part: detection of malicious nodes. I will then describe a case study for the second part --- reshaping a detected terrorist (sub) network.

Toshiharu Sugawara is a professor of Department of Computer Science and Engineering, Waseda University, Japan, since April, 2007. He recieved his B.S. and M.S. degree in Mathematics, 1980 and 1982, respectively, and a Ph.D in Computer Engineering, 1992, from Waseda University. In 1982, he joined Basic Research Laboratories, Nippon Telegraph and Telephone Corporation. From 1992 to 1993, he was a visiting researcher in Department of Computer Science, University of Massachusetts at Amherest, USA. His research interest are: multi-agent systems, distributed artificial intelligence, machine learning, internetworking, network management, information media technology and computer kernel. He is a member of IEEE, ACM, AAAI, Internet Society, Information Processing Society of Japan (IPSJ), Japan Society for Software Science and Technology (JSSST), and Japanese Society of Artificial Intelligence (JSAI).

With recent advance in computer technology, we often expect the situations where agents, which are autonomous programs controlling computer systems and machines like robots, have to collaborate and coordinate with each other (including with human) to solve sophisticated and large problems. Coordination and cooperation are required not only to achieve the overall efficiency but also realize continuous and sustainable operations by complementarily helping each other. In this talk, we discuss the coordination for not only efficient task executions but also complement with each other to make up for frequent regular stops/rests, such as charging of batteries, and with more long-term periodic absences, such as periodic inspection and replacement to new machines. We defined the problem called multi-agent continuous cooperative patrolling problems (MAS-CCPP) that is an extension of multi-agent patrol problem defined in the robotics domain; the main differences are that the task occurrence is expressed probabilistically at any locations in the environment and all agents are inevitably required the interruptions of operations due to battery charge. The MAS-CCPP is the abstract expression of applications such as security patrolling, cooperative information gathering (e.g., from sensors) in a distributed environment and cleaning in a large area.

Our proposed method establishes the division of labor in a bottom-up manner and could achieve the efficient work due to specializing their tasks. We also introduce a simple negotiation protocol to enhance the divisional cooperation. This method could realize not only more effective coordination, but also autonomously generate two types of agents, specialists and generalists. We then found that the generalists contributed to detecting the changes in the environments, and thus, they could enhance the sustainability by reforming so as to adapt to the new environment. We will also explain our recent efforts such as learning of cycle lengths of activities, to cooperatively cover important locations that are required visit more frequently than other normal locations, for example, due to security requirements.

Marco Dorigo received his PhD in electronic engineering in 1992 from Politecnico di Milano. From 1992 to 1993, he was a research fellow at the International Computer Science Institute, Berkeley, CA. Since 1993, he is at Université Libre de Bruxelles (ULB) where in 1996 became a tenured researcher of the F.R.S.-FNRS, the Belgian National Funds for Scientific Research. Between June 2011 and December 2014 he was a full professor of computer science at Paderborn University, Germany. He is now co-director of IRIDIA, the artificial intelligence laboratory of the ULB. He is the Editor-in-Chief of Swarm Intelligence, and associate editor or member of the editorial board of many journals on computational intelligence and adaptive systems. Dr. Dorigo is a Fellow of AAAI, EurAI and IEEE. He was awarded the Italian Prize for Artificial Intelligence in 1996, the Marie Curie Excellence Award in 2003, the F.R.S.-FNRS Quinquennal award in applied sciences in 2005, the Cajastur International Prize for Soft Computing in 2007, an ERC Advanced Grant in 2010, the IEEE Frank Rosenblatt Award in 2015, and the IEEE Evolutionary Computation Pioneer Award, in 2016.

Swarm robotics is about coordinating the activities of a swarm of autonomous robots that cooperate to perform tasks that go beyond the capabilities of the single robots in the swarm. I will present results of experiments run in my lab with homogeneous and heterogeneous swarms of robots that cooperate both physically and logically to perform a number of different tasks. In the talk, I will illustrate how the self-organised nature of the interactions between the robots contributes to the robustness of the robot swarm behaviour and I will discuss some recent research aimed at providing robot swarms with self-healing capabilities.