Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 11128-11150
Abstract
Yuanhe Zhang, Zhenhong Zhou, Wei Zhang, Xinyue Wang, Xiaojun Jia, Yang Liu, Sen Su. Findings of the Association for Computational Linguistics: ACL 2025. 2025.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Dialogue Injection Attack: Jailbreaking LLMs Through Context ManipulationIEEE Transactions on Information Forensics and Security, 2026
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- AI Agents Under Threat: A Survey of Key Security Challenges and Future PathwaysACM Computing Surveys, 2025
- PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning2024
- Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!2024
- A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models2024
- AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models2024
- Red Teaming Language Models with Language Models2022
- Sponge Examples: Energy-Latency Attacks on Neural Networks2021
- Survey of network-based defense mechanisms countering the DoS and DDoS problemsACM Computing Surveys, 2007