164 citations · 204 across the 8 of their papers we have counts for
Showing 2024 · cs.CRShow all
2 papers · 2 filters
cs.CR2024★ 1 cited
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
Danny Halawi, Alexander Wei, Eric Wallace +3
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety…
cs.CR2024★ 8 cited
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Eric Wallace, Kai Xiao, Reimar Leike +3
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompt…