Recent News

REGLO accepted at AAAI 2024

By Wenchao LiDecember 10th, 2023

Congratulations to Feisi, Weichao, Jiameng and our collaborators for having the paper "REGLO: Provable Neural Network Repair for Global Robustness Properties" accepted at AAAI 2024! REGLO is the first technique that enables effective repair of neural networks for global robustness properties.

IARPA TrojAI Phase 2

By Wenchao LiOctober 26th, 2022

Our team (with SRI International and Stony Brook) has been selected for Phase 2 of the TrojAI program. We will develop new technologies to defend AI systems from Trojan attacks.