通过黑盒优化生成隐蔽的过推理提示，让大模型浪费资源却无性能提升。
POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
- 用LLM自身迭代优化生成恶意提示，无需外部数据
- 在多种模型和数据集上实现更优攻击效果
- 适合研究模型安全与对抗攻击的学者
链式思维（CoT）提示技术显著提升了大语言模型的推理能力，使其能通过多步推理解决复杂问题。然而，这种增强的推理过程也带来了新的攻击面，尤其是因冗长无效的推理链条导致计算资源浪费。现有过推理攻击方法通常依赖外部知识源进行数据污染、可检索的中毒内容，以及结构明显的模板，限制了其在真实场景中的实用性。为此，我们提出POT（Prompt-Only OverThinking）——一种新颖的黑盒攻击框架，利用基于LLM的迭代优化生成隐蔽且语义自然的对抗性提示，完全摆脱对外部数据访问和模型检索的依赖。在多种模型架构和数据集上的大量实验表明，POT相较于其他方法表现出更优的攻击性能。
原文摘要 · Abstract (English)
Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving through explicit multi-step reasoning traces. However, these enhanced reasoning processes introduce novel attack surfaces, particularly vulnerabilities to computational inefficiency through unnecessarily verbose reasoning chains that consume excessive resources without corresponding performance gains. Prior overthinking attacks typically require restrictive conditions including access to external knowledge sources for data poisoning, reliance on retrievable poisoned content, and structurally obvious templates that limit practical applicability in real-world scenarios. To address these limitations, we propose POT (Prompt-Only OverThinking), a novel black-box attack framework that employs LLM-based iterative optimization to generate covert and semantically natural adversarial prompts, eliminating dependence on external data access and model retrieval. Extensive experiments across diverse model architectures and datasets demonstrate that POT achieves superior performance compared to other methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。