:::

[2018-12-21] Dr. Lujo Bauer, Carnegie Mellon University, "Adversarial machine learning: curiosity, benefit, or threat?"

專題討論演講公告
Poster:Post date:2018-12-11
Title: Adversarial machine learning: curiosity, benefit, or threat?
Date: 2018-12-21 3:40pm-4:40pm
Location: R102, CSIE
Speaker: Dr. Lujo Bauer, Carnegie Mellon University
Hosted by: Prof. Hsu-Chun Hsiao
 
 

Abstract:

 
This talk examines whether we should be concerned about the increasing use of machine-learning (ML) algorithms in safety- and security-critical applications. Focusing on state-of-the-art face-recognition algorithms, I will show that machine learning can be vulnerable to _physically realizable_ and _inconspicuous_ attacks, allowing attackers to evade recognition or impersonate specific people. I will describe a systematic method to automatically generate such attacks, which are realized through printing a pair of eyeglass frames on a consumer photo printer. I will also discuss other domains where such attacks may play a role, as well as whether similar techniques can be used to help, instead of hinder, security and privacy.
 
 
Biography:
 
Lujo Bauer is an Associate Professor of Electrical and Computer Engineering, and of Computer Science, at Carnegie Mellon University. He received his B.S. in Computer Science from Yale University in 1997 and his Ph.D., also in Computer Science, from Princeton University in 2003. Dr. Bauer is a member of CyLab, Carnegie Mellon's computer security and privacy research institute, and serves as the director of CyLab's Cyber Autonomy Research Center.
 
Dr. Bauer's research interests span many areas of computer security and privacy, and include building usable access-control systems with sound theoretical underpinnings, developing languages and systems for run-time enforcement of security policies on programs, and generally narrowing the gap between a formal model and a practical, usable system. His recent work focuses on developing tools and guidance to help users stay safer online and in examining how advances in machine learning can lead to a more secure future.
 
Dr. Bauer served as the program chair for the flagship computer security conferences of the IEEE (S&P 2015) and the Internet Society (NDSS 2014) and is an associate editor of ACM Transactions on Privacy and Security.
 
 
Last modification time:2018-12-11 AM 10:23

cron web_use_log