Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912393916841984 |
|---|---|
| author | Zhang, Yuanhe Zhou, Zhenhong Zhang, Wei Wang, Xinyue Jia, Xiaojun Liu, Yang Su, Sen |
| author_facet | Zhang, Yuanhe Zhou, Zhenhong Zhang, Wei Wang, Xinyue Jia, Xiaojun Liu, Yang Su, Sen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13879 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings Zhang, Yuanhe Zhou, Zhenhong Zhang, Wei Wang, Xinyue Jia, Xiaojun Liu, Yang Su, Sen Computation and Language Artificial Intelligence Cryptography and Security 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. |
| title | Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2412.13879 |