196 citations · 724 across the 42 of their papers we have counts for
44 papers
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar +9
For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: do…
Improving Alignment and Robustness with Circuit Breakers
Andy Zou, Long Phan, Justin Wang +7
AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interr…
LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses
Weiran Lin, Anna Gerchanovsky, Omer Akgul +3
Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such service…
VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices
Han Zhang, Zifan Wang, Mihir Dhamankar +2
Many Internet-of-Things (IoT) devices rely on cloud computation resources to perform machine learning inferences. This is expensive and may raise privacy concerns for users. Consum…
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Kai Hu, Weichen Yu, Yining Li +7
Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level att…
Transfer Attacks and Defenses for Large Language Models on Coding Tasks
Chi Zhang, Zifan Wang, Ravi Mangal +3
Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previ…