Timezone: »

 
Competition
The Trojan Detection Challenge
Mantas Mazeika · Dan Hendrycks · Huichen Li · Xiaojun Xu · Andy Zou · Sidney Hough · Arezoo Rajabi · Dawn Song · Radha Poovendran · Bo Li · David Forsyth

Thu Dec 08 01:00 PM -- 04:00 PM (PST) @ Virtual
Event URL: https://trojandetection.ai »

A growing concern for the security of ML systems is the possibility for Trojan attacks on neural networks. There is now considerable literature for methods detecting these attacks. We propose the Trojan Detection Challenge to further the community's understanding of methods to construct and detect Trojans. This competition will consist of complimentary tracks on detecting/analyzing Trojans and creating evasive Trojans. Participants will be tasked with devising methods to better detect Trojans using a new dataset containing over 6,000 neural networks. Code and evaluations from three established baseline detectors will provide a starting point, and a novel Minimal Trojan attack will challenge participants to push the state-of-the-art in Trojan detection. At the end of the day, we hope our competition spurs practical innovations and clarifies deep questions surrounding the offense-defense balance of Trojan attacks.

Author Information

Mantas Mazeika (University of Illinois Urbana-Champaign)
Dan Hendrycks (Center for AI Safety)
Huichen Li (UIUC)
Xiaojun Xu (University of Illinois at Urbana-Champaign)
Andy Zou (CMU)
Sidney Hough (Stanford)
Arezoo Rajabi (UW)
Dawn Song (UC Berkeley)
Radha Poovendran (University of Washington, Seattle)
Bo Li (UIUC)
David Forsyth (University of Illinois at Urbana-Champaign)

More from the Same Authors