28 citations · 59 across the 4 of their papers we have counts for
4 papers
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…
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Mantas Mazeika, Long Phan, Xuwang Yin +9
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a sta…
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
Alexander Pan, Jun Shern Chan, Andy Zou +7
Artificial agents have traditionally been trained to maximize reward, which may incentivize power-seeking and deception, analogous to how next-token prediction in language models (…
Papaya: Federated Learning, but Fully Decentralized
Ram M Kripa, Andy Zou, Ryan Jia +1
Federated Learning systems use a centralized server to aggregate model updates. This is a bandwidth and resource-heavy constraint and exposes the system to privacy concerns. We ins…