Institution
ETH ZurichRoles and affiliations follow the cited source. A source check is not an independent replication.
More filters → 
University of Waterloo
FAR.AI
University of TorontoETH Zurich
Massachusetts Institute of Technology
Vector Institute
QuestionHow robust are open-weight safeguards to modifications that preserve useful capability?
Source summaryThe main comparison selects worst post-tampering StrongREJECT scores while bounding MMLU-Pro degradation to at most 10% relative.
NUWA research note · independent review pending
QuestionDoes increasing clean-data scale dilute a fixed adversarial insertion enough to prevent a backdoor?
Source summaryComparable insertion counts can affect models trained on substantially different amounts of clean data.
NUWA research note · independent review pending
QuestionCan tool-using agents maintain utility while processing attacker-controlled external data?
Source summaryAgents fail some benign tasks even without attacks.
NUWA research note · independent review pending · Contains: question / method / limits
NUWA 
