AIBearisharXiv – CS AI · 6h ago7/10
🧠
Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
Researchers have developed an A*-inspired framework that generates obfuscated prompts capable of triggering factual errors in large language models while preserving semantic intent. The method uses a hierarchical rewrite strategy with dynamic semantic dispersion to efficiently create adversarial prompts, demonstrating higher attack success rates than existing approaches and raising urgent concerns about LLM reliability in safety-critical applications.