Penny's paper "MISA: Online Defense of Trojaned Models using Misattributions" has been accepted at ACSAC'21. Congratulations to Penny and our collaborators at SRI International.
Congratulations to Jiameng!
Congratulations to Jiameng! We achieve the state-of-the-art results for training neural networks with provable l_\infty robustness. Preprint available at https://arxiv.org/abs/2008.06081.
Please consider sending your strong papers to this track.
We will be working with SRI International and Stony Brook University on Trojan Detection using Attribution, Counterfactuals, and Topological Analysis under the IARPA TrojAI Program.
Congratulations to Weichao and our collaborators! This paper introduces the concepts of policy repair and minimally deviating policy repair for learning-based controllers.
Our paper "Divide and Slide: Layer-Wise Refinement for Output Range Analysis of Deep Neural Networks" has been accepted to EMSOFT 2020. Congratulations to Jiameng and our collaborators at Northwestern and Dayton!
Our tool paper "ReachNN*: A Tool for Reachability Analysis of Neural-Network Controlled Systems" has been accepted to ATVA 2020. Congratulations to Jiameng and our collaborators at Northwestern and Dayton!