Lune

EMNLP Findings2025

PD³F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models

Yuanhe Zhang, Xinyue Wang, Haoran Gao, Zhenhong Zhou, Fanyu Meng, Yuyao Zhang, Sen Su

Abstract

Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denialof-service (DoS) attacks designed for LLMs. However, existing works lack mitigation strategies against such threats, resulting in unresolved security risks for real-world LLM deployments. To this end, we propose the Pluggable and Dynamic DoS-Defense Framework (PD 3 F), which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides. On the input side, we propose the Resource Index to guide Dynamic Request Polling Scheduling, thereby reducing resource usage induced by malicious attacks under high-concurrency scenarios. On the output side, we introduce the Adaptive End-Based Suppression mechanism, which terminates excessive malicious generation early. Experiments across six models demonstrate that PD 3 F significantly mitigates resource consumption attacks, improving users' access capacity by up to 500% during adversarial load. PD 3 F represents a step toward the resilient and resource-aware deployment of LLMs against resource consumption attacks. Our code is available at https: //github.com/shuita2333/PDF_defense.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Measuring Massive Multitask Language Understanding cites Aligning AI With Shared Human Values
  • Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites Aligning AI With Shared Human Values
  • Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on21

  1. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  2. Jailbroken: How Does LLM Safety Training Fail?Alexander Wei, Nika Haghtalab, Jacob SteinhardtNeurIPS 2023 · 2,230 citations
  3. Aligning AI With Shared Human ValuesDan Hendrycks, Collin Burns, Steven Basart, Andrew Critch et al.ICLR 2021 · 878 citations
  4. Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson et al.NeurIPS 2024 · 835 citations
  5. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations

Related papers

  1. Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box SettingsYuanhe Zhang, Zhenhong Zhou, Wei Zhang, Xinyue Wang et al.ACL Findings 2025 · 6 citations
  2. ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite ThinkingYunzhe Li, Jianan Wang, Hongzi Zhu, James Lin et al.NDSS 2026 · 26 citations
  3. Autonomy Comes with Costs: Detecting Denial-of-Service Vulnerabilities Caused by Resource Abusing in LLM-based AgentsJiaqi Luo, Jiarun Dai, Fengyu Liu, Songyang Peng et al.USENIX Security 2026
  4. Imperceptible Content Poisoning in LLM-Powered ApplicationsQuan Zhang, Chijin Zhou, Gwihwan Go, Binqi Zeng et al.ASE 2024 · 3 citations
  5. Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM SecurityXiang Fang, Wanlong FangAAAI 2026 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines