{"ID":2921856,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T19:49:55.6428996Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01441","arxiv_id":"2606.01441","title":"Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts","abstract":"Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations. This vulnerability is urgent, as LLMs are rapidly integrated into safety-critical domains where factual reliability is non-negotiable. Existing attack methods either lack efficiency or fail to capture the adaptive strategies of real-world adversaries. We propose an A*-inspired Factual Error Induction Framework, a framework for generating semantically aligned yet obfuscated prompts. At its core is a Hierarchical Rewrite Strategy guided by a dynamic semantic dispersion coefficient $γ$ that balances conservative edits early with aggressive obfuscations later, following a reverse simulated annealing schedule. To enhance interpretability, we further introduce Agentic Mechanism Labeling, which discovers and refines adversarial mechanisms, offering interpretable reverse optimization. Theoretically, we prove that prompt rewriting follows a contractive recurrence, leading to semantic collapse as $γ$ decreases. Empirically, across diverse LLMs, our method achieves higher attack success rates than exhaustive exploration while requiring fewer attempts, demonstrating both efficiency and effectiveness.","short_abstract":"Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations. This vulnerability is urgent, as LLMs are rapidly integrated into safety-critical domains where factual reliability is...","url_abs":"https://arxiv.org/abs/2606.01441","url_pdf":"https://arxiv.org/pdf/2606.01441v1","authors":"[\"Boxuan Wang\",\"Zhuoyun Li\",\"Xiaowei Huang\",\"Yi Dong\"]","published":"2026-05-31T20:20:53Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}