提出黑盒场景下自动生成攻击，使大模型服务延迟超250倍
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
- 构建攻击树并迭代优化，实现跨模型单提示攻击
- 实测使服务延迟提升250倍以上，显著消耗显存与算力
- 植入长度后门可绕过现有防御，适合安全研究者参考
大型语言模型（LLMs）在多项任务中表现卓越，但仍面临外部威胁，尤其是大模型拒绝服务（LLM-DoS）攻击。此类攻击旨在耗尽计算资源并阻断服务。然而，现有研究多聚焦于白盒攻击，黑盒场景仍缺乏深入探索。本文提出面向黑盒大模型的自动生成式拒绝服务攻击（AutoDoS），通过构建DoS攻击树并扩展节点覆盖率，在黑盒条件下实现高效攻击。借助可迁移性驱动的迭代优化，AutoDoS可在单一提示中适配不同模型。此外，实验表明嵌入长度特洛伊木马可更有效规避现有防御机制。结果表明，AutoDoS使服务响应延迟提升超过250倍，导致显卡利用率和内存占用严重升高。本工作为大模型安全防御提供了新视角。代码已开源：https://github.com/shuita2333/AutoDoS。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS) attacks. Specifically, LLM-DoS attacks aim to exhaust computational resources and block services. However, existing studies predominantly focus on white-box attacks, leaving black-box scenarios underexplored. In this paper, we introduce Auto-Generation for LLM-DoS (AutoDoS) attack, an automated algorithm designed for black-box LLMs. AutoDoS constructs the DoS Attack Tree and expands the node coverage to achieve effectiveness under black-box conditions. By transferability-driven iterative optimization, AutoDoS could work across different models in one prompt. Furthermore, we reveal that embedding the Length Trojan allows AutoDoS to bypass existing defenses more effectively. Experimental results show that AutoDoS significantly amplifies service response latency by over 250$\times\uparrow$, leading to severe resource consumption in terms of GPU utilization and memory usage. Our work provides a new perspective on LLM-DoS attacks and security defenses. Our code is available at https://github.com/shuita2333/AutoDoS.
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。