Our new paper on neural network repair has been accepted at ICLR'22. Congrats to Feisi!
Our paper "Programmatic Reward Design by Example" has been accepted at AAAI'22. Congrats to Weichao!
Our paper "Opportunistic Communication with Latency Guarantees for Intermittently-Powered Devices" has been accepted at DATE'22. Congrats to Kacper and our collaborators at UC Riverside and Pitt!
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.