TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Stress-tests open-weight model safeguards under fine-tuning and representation-level tampering while tracking utility.
Verify byline in the original ↗PUBLICATION BYLINE
Indexed publications with this author name. Affiliation and author identity require publication-specific evidence.
Stress-tests open-weight model safeguards under fine-tuning and representation-level tampering while tracking utility.
Verify byline in the original ↗Studies pretraining-data filtering as a safeguard against biothreat proxy knowledge and tests resistance to adversarial fine-tuning.
Verify byline in the original ↗