13 citations · 13 across the 2 of their papers we have counts for
2 papers
cs.CR2026
Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
David Campbell, Neil Kale, Udari Madhushani Sehwag +5
Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures…
cs.LG2024★ 13 cited
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…