@inproceedings{zhang-etal-2025-crabs,
    title = "Crabs: Consuming Resource via Auto-generation for {LLM}-{D}o{S} Attack under Black-box Settings",
    author = "Zhang, Yuanhe  and
      Zhou, Zhenhong  and
      Zhang, Wei  and
      Wang, Xinyue  and
      Jia, Xiaojun  and
      Liu, Yang  and
      Su, Sen",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.findings-acl.580/",
    doi = "10.18653/v1/2025.findings-acl.580",
    pages = "11128--11150",
    ISBN = "979-8-89176-256-5",
    abstract = "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 ($\textbf{AutoDoS}$) 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 $\textbf{250}\times\uparrow$, 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."
}