Program Highlights »
Fri Dec 8th 08:00 AM -- 06:30 PM @ Hyatt Hotel, Shoreline
Machine Learning and Computer Security
Jacob Steinhardt · Nicolas Papernot · Bo Li · Chang Liu · Percy Liang · Dawn Song

Workshop Home Page

While traditional computer security relies on well-defined attack models and proofs of security, a science of security for machine learning systems has proven more elusive. This is due to a number of obstacles, including (1) the highly varied angles of attack against ML systems, (2) the lack of a clearly defined attack surface (because the source of the data analyzed by ML systems is not easily traced), and (3) the lack of clear formal definitions of security that are appropriate for ML systems. At the same time, security of ML systems is of great import due the recent trend of using ML systems as a line of defense against malicious behavior (e.g., network intrusion, malware, and ransomware), as well as the prevalence of ML systems as parts of sensitive and valuable software systems (e.g., sentiment analyzers for predicting stock prices). This workshop will bring together experts from the computer security and machine learning communities in an attempt to highlight recent work in this area, as well as to clarify the foundations of secure ML and chart out important directions for future work and cross-community collaborations.

09:00 AM Opening Remarks
Dawn Song
09:15 AM AI Applications in Security at Ant Financial (Invited Talk)
Alan Qi
09:45 AM A Word Graph Approach for Dictionary Detection and Extraction in DGA Domain Names (Contributed Talk)
Mayana Pereira
10:00 AM Practical Machine Learning for Cloud Intrusion Detection (Contributed Talk)
Ram Shankar Siva Kumar
10:15 AM Poster Spotlights I (Spotlight Session)
Taesik Na, Yang Song, Aman Sinha, Richard Shin, Qiuyuan Huang, Nina Narodytska, Matt Staib, Kexin Pei, Suyee Suya, Amirata Ghorbani, Jacob Buckman, Matthias Hein, Huan Zhang, Yanjun Qi, Yuan Tian, Min Du, Dimitris Tsipras
11:00 AM International Security and the AI Revolution (Invited Talk)
Allan Dafoe
11:30 AM BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain (Contributed Talk)
Siddharth Garg
11:45 AM Poster Spotlights II (Spotlight Session)
01:30 PM Defending Against Adversarial Examples (Invited Talk)
Ian Goodfellow
02:00 PM Provable defenses against adversarial examples via the convex outer adversarial polytope (Contributed Talk)
J. Zico Kolter
02:15 PM Games People Play (With Bots) (Invited Talk)
Donald Brinkman
02:45 PM Synthesizing Robust Adversarial Examples (Contributed Talk / Demo)
Andrew Ilyas, Anish Athalye, Logan Engstrom, Kevin Kwok
03:00 PM Poster Session
03:45 PM Safety beyond Security: Societal Challenges for Machine Learning (Invited Talk)
Moritz Hardt
04:15 PM Towards Verification of Deep Neural Networks (Invited Talk)
Clark Barrett