4 papers
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
Domenic Rosati, Ali Dadsetan, Hong Huang +5
A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech. Preventing su…
Limits of Convergence-Rate Control for Open-Weight Safety
Domenic Rosati, Xijie Zeng, Hong Huang +4
Open-weight foundation models can be fine-tuned for harmful purposes after release, yet no existing training resistance methods provide theoretical guarantees. Treating these inter…
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk +12
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…