← authors · overview

• Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
  2023 · 1086 citations
• Sorry-bench: Systematically Evaluating Large Language Model Safety Refusal
  2024 · 168 citations
• Algorithm Of Thoughts: Enhancing Exploration Of Ideas In Large Language Models
  2023 · 108 citations
• Rigorllm: Resilient Guardrails For Large Language Models Against Undesired Content
  2024 · 76 citations
• Practical Membership Inference Attacks Against Large-scale Multi-modal Models: A Pilot Study
  2023 · 49 citations