Computer Science Colloquium Series: Bimal Viswanath
April 09, 2018
12:00 PM - 01:00 PM
Wegmans Hall 1400 (auditorium), River Campus
University of California Santa Barbara
TITLE: Security in an AI-driven world
ABSTRACT: AI based on deep neural networks (DNN) has transformed computing as we know it. As AI tools become commoditized, and we increasingly rely on online services/devices powered by AI, it is important to understand the security risks. In this talk, I will present two research directions on this topic.
First, I will describe how AI can be used for attacks--to manipulate the information we consume online. In limited application contexts, DNNs have reached a point where they can produce sufficiently clear and correct text effectively indistinguishable from those produced by humans. I will show that AI programs based on Recurrent Neural Networks (RNNs) are capable of generating deceptive yet realistic looking reviews targeting e-commerce sites, and also discuss defensive measures. Second, I will focus on attacks on AI systems. Transfer learning is viewed as the next big step in accelerating adoption of AI systems. In this scheme, a small number of highly tuned centralized models are shared with the general community, and individual users further customize the model for a given application with additional training. I will present practical misclassification attacks against DNN models derived using transfer learning services available today. As part of future plans, I will discuss the need to re-think data-driven security when considering an AI-powered adversary.
BIO: Bimal Viswanath is a Postdoctoral Scholar at the University of California Santa Barbara, and is currently visiting the University of Chicago. Prior to that, he was a Researcher at Nokia Bell Labs, Germany for a year. H