New IARPA Project on Detecting Trojans in Neural Networks
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.
Author: Wenchao Li
Assistant Professor of ECE@BU
New paper accepted at RV’20.
Congratulations to Weichao and our collaborators! This paper introduces the concepts of policy repair and minimally deviating policy repair for learning-based controllers.
New paper accepted at EMSOFT’20
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!
New tool paper accepted at ATVA’20
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!
Two papers accepted at DAC’20.
Our TrojDRL work appears in Wired today! We thank Will Knight and Wired Magazine for the coverage.
https://www.wired.com/story/tainted-data-teach-algorithms-wrong-lessons/
New paper accepted at DATE 2020
Paper on Application-Aware Scheduling of Networked Applications over the Low-Power Wireless Bus accepted at DATE’20. Congratulations Kacper!
New NSF CPS Project with Roberto Tron and Cristina Nita-Rotaru
Securing multi-agent systems through physical cognition and control synthesis: Project website: http://sites.bu.edu/securingmas/ NSF Award: https://nsf.gov/awardsearch/showAward?AWD_ID=1932162
New ONR Project with Qi Zhu and Hyoseung Kim
This project will develop the foundations of a cross-layer paradigm for building adaptive, dependable and secure systems under weakly-hard real-time constraints.
Invited to serve on the TPC of DAC 2020
https://www.dac.com/call-for-contributions