通过无限思考诱导黑盒大模型崩溃,实现低消耗拒绝服务攻击
ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking
- 将离散输入映射到连续空间,利用稀疏性在低维空间优化恶意提示
- 仅用少量令牌使商用大模型吞吐量降至1%甚至完全失效
- 适用于评估黑盒大模型安全风险,尤其适合安全研究人员
大语言模型已成为自然语言理解与生成、具身智能和科学发现等应用的核心组件。随着计算需求增长,这些模型越来越多以云服务形式部署,用户可通过互联网访问。然而,这种部署模式引入了新型威胁:通过无界推理发起的拒绝服务(DoS)攻击。攻击者设计特殊输入,使模型陷入过长或无限生成循环,耗尽后端计算资源,导致合法用户服务降级或中断。为应对风险,许多模型提供商采用闭源黑盒设置以隐藏内部机制。本文提出ThinkTrap,一种针对黑盒大模型服务的新型输入空间优化框架,可在不依赖模型内部信息的情况下实施DoS攻击。其核心思想是将离散标记映射至连续嵌入空间,在低维子空间中利用输入稀疏性进行高效黑盒优化,目标是找到能引发长时间或非终止生成的对抗性提示,以极低的令牌开销实现服务瘫痪。我们在多个商业闭源大模型服务上评估该攻击。结果表明,即使远低于平台通常限制的请求频率(普遍为每分钟10次,即10 RPM),该攻击仍可使服务吞吐量下降至原始能力的1%,部分场景下甚至导致完全服务失效。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as cloud-based services, allowing users to access powerful LLMs via the Internet. However, this deployment model introduces a new class of threat: denial-of-service (DoS) attacks via unbounded reasoning, where adversaries craft specially designed inputs that cause the model to enter excessively long or infinite generation loops. These attacks can exhaust backend compute resources, degrading or denying service to legitimate users. To mitigate such risks, many LLM providers adopt a closed-source, black-box setting to obscure model internals. In this paper, we propose ThinkTrap, a novel input-space optimization framework for DoS attacks against LLM services even in black-box environments. The core idea of ThinkTrap is to first map discrete tokens into a continuous embedding space, then undertake efficient black-box optimization in a low-dimensional subspace exploiting input sparsity. The goal of this optimization is to identify adversarial prompts that induce extended or non-terminating generation across several state-of-the-art LLMs, achieving DoS with minimal token overhead. We evaluate the proposed attack across multiple commercial, closed-source LLM services. Our results demonstrate that, even far under the restrictive request frequency limits commonly enforced by these platforms, typically capped at ten requests per minute (10 RPM), the attack can degrade service throughput to as low as 1% of its original capacity, and in some cases, induce complete service failure.
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。