Abstract:

Two technologies are growing in importance — AI and Cybersecurity. Not only are they individually important, their intersection is also

growing in importance. Large data is now available to detect attacks. These come from not just the traditional sensors like those on

networks and hosts, but also from textual sources such as web fora, dark web, and threat intelligence feeds. AI can help us make sense

of these large volumes of data to support SoC analysts in their tasks. However, as we deploy AI systems, they also present a new attack

surfaces for adversaries to exploit. Attacks range from poisoning the models being learned, fooling them with adversarial examples, and

inferring the data that was used to train the model. In this talk, we will explore both these elements. While we will also introduce our research,

the primary purpose is to make the audience aware of the challenges and developments in this space.

Bio

Anupam Joshi is the Oros Family Professor and Chair of Computer Science and Electrical Engineering Department at the University of Maryland, Baltimore County (UMBC). He is the Director of UMBC’s Center for Cybersecurity. He is a Fellow of IEEE. Dr. Joshi obtained a B.Tech degree from IIT Delhi in 1989, and a Masters and Ph.D. from Purdue University in 1991 and 1993 respectively. His research interests are in the broad area of networked computing and intelligent systems. His primary focus has been on data management and security/privacy in mobile/pervasive computing environments, and policy driven approaches to security and privacy. He is also interested in Semantic Web and Data/Text/Web Analytics, especially their applications to (cyber) security and healthcare. He has published over 275 technical papers with an h-index of 86 and over 28000 citations (per Google scholar), been granted nine patents, and has obtained research support from National Science Foundation (NSF), NASA, Defense Advanced Research Projects Agency (DARPA), US Dept of Defense (DoD), NIST, IBM, Microsoft.