mlsanityData to 7 Oct 2026

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings

arXiv 2412.13879 ↗First posted 18 Dec 2024cs.CL cs.AI cs.CRcited by 33

Not on the map. Why?

Abstract (arXiv)

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×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.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

46 of 67 references.

References · 46

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  10. 2024Qwen2 Technical Reportcited by 2,076
  11. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  12. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
34 more
  1. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  2. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  3. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  4. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  5. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  6. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  7. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
  8. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  9. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  10. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  11. 2023Detecting Language Model Attacks with Perplexitycited by 411
  12. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 324
  13. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  14. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  15. 2023Poisoning Language Models During Instruction Tuningcited by 254
  16. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  17. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Surveycited by 215
  18. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 183
  19. 2023LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70Bcited by 183
  20. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  21. 2021Challenges in Detoxifying Language Modelscited by 169
  22. 2024AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMscited by 160
  23. 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 157
  24. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attackscited by 135
  25. 2023Explore, Establish, Exploit: Red Teaming Language Models from Scratchcited by 111
  26. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  27. 2024Coercing LLMs to do and reveal (almost) anythingcited by 88
  28. 2024Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagescited by 69
  29. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 63
  30. 2024Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoningcited by 62
  31. 2024Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!cited by 36
  32. 2024A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systemscited by 15
  33. 2024Vocabulary Attack to Hijack Large Language Model Applicationscited by 12
  34. 2024Playing Language Game with LLMs Leads to Jailbreakingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 20.

33 papers.

Sort:

By area:

  1. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  2. 2026A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypescited by 19
  3. 2025CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Modelscited by 18
  4. 2025Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systemscited by 17
  5. 2026Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agentscited by 14
  6. 2026Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agentscited by 14
  7. 2025Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning Systemcited by 10
  8. 2025LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loopscited by 9
  9. 2026ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Modelscited by 5
  10. 2026RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflectioncited by 4
  11. 2025Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimizationcited by 3
  12. 2025Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmarkcited by 3
21 more
  1. 2026BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Promptscited by 3
  2. 2025Resource Consumption Red-Teaming for Large Vision-Language Modelscited by 2
  3. 2025Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Modelscited by 2
  4. 2025RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stresscited by 2
  5. 2026Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Modelcited by 2
  6. 2026LLM-enabled Applications Require System-Level Threat Monitoringcited by 2
  7. 2026Resource Consumption Threats in Large Language Modelscited by 2
  8. 2026Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agentscited by 2
  9. 2025PD3F: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Modelscited by 1
  10. 2025VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Modelscited by 1
  11. 2026SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attackscited by 1
  12. 2026LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Modelscited by 1
  13. 2026Inference Cost Attacks for Retrieval-Augmented Large Language Modelscited by 1
  14. 2026From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrailscited by 1
  15. 2025An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMscited by 0
  16. 2026Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMscited by 0
  17. 2026VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Modelscited by 0
  18. 2026Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injectioncited by 0
  19. 2026Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Modelscited by 0
  20. 2026SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agentscited by 0
  21. 2026Uncovering Uncontrolled Repetition through Residual Stream Dynamicscited by 0