10 papers
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…
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Yuancheng Xu, Udari Madhushani Sehwag, Alec Koppel +4
Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human prefe…
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An +5
We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator…
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
Bang An, Sicheng Zhu, Ruiyi Zhang +3
Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not…
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya +5
As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding…
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess +1
With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has inc…