Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911738709934080 |
|---|---|
| author | Wang, Boxuan Li, Zhuoyun Huang, Xiaowei Dong, Yi |
| author_facet | Wang, Boxuan Li, Zhuoyun Huang, Xiaowei Dong, Yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01441 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts Wang, Boxuan Li, Zhuoyun Huang, Xiaowei Dong, Yi Artificial Intelligence 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. |
| title | Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2606.01441 |