Yawen Duan

Publications

Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google

Robustness

DeepSeek-R1 has recently made waves as a state-of-the-art open-weight model, with potentially substantial improvements in model efficiency and reasoning. But like other open-weight models and leading fine-tunable proprietary models such as OpenAI’s GPT-4o, Google’s Gemini 1.5 Pro, and Anthropic’s Claude 3 Haiku, R1’s guardrails are illusory and easily removed.

February 3, 2025
Date Range

Adversarial Policies Beat Superhuman Go AIs

Robustness

We describe an attack on the state-of-the-art Go-playing AI system, KataGo. The adversaries do not win by learning to play Go better than KataGo but instead by tricking KataGo into making serious blunders, demonstrating that even superhuman AI systems may harbor surprising failure modes.

January 8, 2023
Date Range

News

Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google

Red-Teaming & Evaluation

DeepSeek-R1 has recently made waves as a state-of-the-art open-weight model, with potentially substantial improvements in model efficiency and reasoning. But like other open-weight models and leading fine-tunable proprietary models such as OpenAI’s GPT-4o, Google’s Gemini 1.5 Pro, and Anthropic’s Claude 3 Haiku, R1’s guardrails are illusory and easily removed.

February 3, 2025
Date Range

Research

Our research explores a portfolio of high-potential agendas.

Events

Our events bring together global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI