Institution

University of Waterloo

Roles and affiliations follow the cited source. A source check is not an independent replication.

More filters →

University of Waterloo ↗

Risk EvaluationBenchmark

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

Research by University of Waterloo FAR.AI University of Toronto ETH Zurich Massachusetts Institute of Technology Vector Institute

2026-02-06

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

Cross-cutting researchBehavior

Read source note Original source ↗