Secure Deep Reinforcement Learning
Deep RL has emerged as an important family of techniques for training autonomous agents and has led to the achievement of human-level performance on complex games such as Atari, Go, and Starcraft. However, at the same time, deep RL is also vulnerable to adversarial examples and can overfit to the training environment. In this talk, I will talk about our recent work in adversarial examples in deep RL and a framework for investigating generalization in deep RL towards the goal of building deep RL with greater resilience and generalization.
Dawn Song is a Professor in the Department of Electrical Engineering and Computer Science at UC Berkeley. Her research interest lies in deep learning, security, and blockchain. She has studied diverse security and privacy issues in computer systems and networks, including areas ranging from software security, networking security, distributed systems security, applied cryptography, blockchain and smart contracts, to the intersection of machine learning and security. She is the recipient of various awards including the MacArthur Fellowship, the Guggenheim Fellowship, the NSF CAREER Award, the Alfred P. Sloan Research Fellowship, the MIT Technology Review TR-35 Award, the Faculty Research Award from IBM, Google and other major tech companies, and Best Paper Awards from top conferences in Computer Security and Deep Learning. She is an IEEE Fellow. She is ranked the most cited scholar in computer security (AMiner Award). She obtained her Ph.D. degree from UC Berkeley. Prior to joining UC Berkeley as a faculty, she was a faculty at Carnegie Mellon University from 2002 to 2007. She is also a serial entrepreneur.