arxiv.orgpaper

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack

ReasAlign is a model-level safety alignment technique that defends LLM agents against indirect prompt injection by adding structured reasoning steps to detect conflicting instructions embedded in external data and preserve the user's original task intent. It also uses a test-time scaling mechanism with a preference-optimized judge model to score and select the best reasoning trajectory. On the CyberSecEval2 benchmark it reports 94.6% utility with only 3.6% attack success rate, substantially outperforming Meta SecAlign, which scores 56.4% utility with a 74.4% attack success rate.