4 papers · 1 filter
Representation Engineering: A Top-Down Approach to AI Transparency
Andy Zou, Long Phan, Sarah Chen +18
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights f…
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…
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…
A Recipe for Improved Certifiable Robustness
Kai Hu, Klas Leino, Zifan Wang +1
Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported bot…