Deep learning has made huge advances and impact in many areas of computer science such as vision, speech, NLP, and Robotics. Many exciting research questions lie in the intersection of security and deep learning.
First, how will these deep learning systems behave in the presence of adversaries? Research has shown that many of the state-of-the-art deep learning systems can be easily fooled by adversarial examples. We will explore fundamental questions in this area including what types of attacks are possible on deep learning systems, why they exist, and how we can defend against them.
Second, how can deep learning techniques help security applications? We will explore this area and study example security applications using deep learning techniques including program binary analysis, password security analysis, malware detection and fraud detection
For more information and future announcements in deep learning and security, sign up on the mailing list.
Speakers and instructors
Program chair: Dawn Song
Invited speakers: Lujo Bauer, Zhifeng Geng, Xiaodong Su
Lab and hackathon instructors: Chang Liu, Jernej Kos
9:00 - 9:10am - Overview of the workshop. Dawn Song.
9:10 - 10:10am - Introduction and overview of deep learning and security. Dawn Song.
10:10 - 10:30am - Break
10:30 - 12:00 - Introduction and overview of adversarial deep learning. Chang Liu and Dawn Song.
12:00 - 1:00pm - Lunch
1:00 - 2:00pm - Invited talk: Machine Learning in Computer Security for Fun and Profit: Password Meters, Face Recognition and Online Tracking. Lujo Bauer.
2:00 - 3:00pm - Invited talk: Discover Maliciousness Among URLs: A Deep Learning Approach. Zhifeng Geng and Xiaodong Su.
3:00 - 3:30pm - Break
3:30 Feb 19 - 5:00pm Feb 20 - Deep Learning and Security Innovation Hackathon.