2 papers
cs.LG2026
From Shallow to Deep: Pinning Semantic Intent via Causal GRPO
Shuyi Zhou, Zeen Song, Wenwen Qiang +4
Large Language Models remain vulnerable to adversarial prefix attacks (e.g., ``Sure, here is'') despite robust standard safety. We diagnose this vulnerability as Shallow Safety Ali…
cs.CL2026
Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
Yao Zhou, Zeen Song, Wenwen Qiang +4
Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building on this observation, we m…