{"ID":2841151,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11961","arxiv_id":"2511.11961","title":"\"Power of Words\": Stealthy and Adaptive Private Information Elicitation via LLM Communication Strategies","abstract":"While communication strategies of Large Language Models (LLMs) are crucial for human-LLM interactions, they can also be weaponized to elicit private information, yet such stealthy attacks remain under-explored. This paper introduces the first adaptive attack framework for stealthy and targeted private information elicitation via communication strategies. Our framework operates in a dynamic closed-loop: it first performs real-time psychological profiling of the users' state, then adaptively selects an optimized communication strategy, and finally maintains stealthiness through prompt-based rewriting. We validated this framework through a user study (N=84), demonstrating its generalizability across 3 distinct LLMs and 3 scenarios. The targeted attacks achieved a 205.4% increase in eliciting specific targeted information compared to stealthy interactions without strategies. Even stealthy interactions without specific strategies successfully elicited private information in 54.8% cases. Notably, users not only failed to detect the manipulation but paradoxically rated the attacking chatbot as more empathetic and trustworthy. Finally, we advocate for mitigations, encouraging developers to integrate adaptive, just-in-time alerts, users to build literacy against specific manipulative tactics, and regulators to define clear ethical boundaries distinguishing benign persuasion from coercion.","short_abstract":"While communication strategies of Large Language Models (LLMs) are crucial for human-LLM interactions, they can also be weaponized to elicit private information, yet such stealthy attacks remain under-explored. This paper introduces the first adaptive attack framework for stealthy and targeted private information elici...","url_abs":"https://arxiv.org/abs/2511.11961","url_pdf":"https://arxiv.org/pdf/2511.11961v1","authors":"[\"Shuning Zhang\",\"Jiaqi Bai\",\"Linzhi Wang\",\"Shixuan Li\",\"Xin Yi\",\"Hewu Li\"]","published":"2025-11-15T00:16:23Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}