$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models

• URL: http://arxiv.org/abs/2505.18680v1
• Date: Sat, 24 May 2025 12:54:22 GMT
• Title: $PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models
• Abstract summary: Large Language Models (LLMs) are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes.<n>We propose the Pluggable and Dynamic DoS-Defense Framework ($PD3F$), which employs a two-stage approach to defend against resource consumption attacks.<n>$PD3F$ significantly mitigates resource consumption attacks, improving users' access capacity by up to 500% during adversarial load.
• Score: 9.585089414738542
• License: http://creativecommons.org/licenses/by/4.0/
• 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 denial-of-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 ($PD^3F$), 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 $PD^3F$ significantly mitigates resource consumption attacks, improving users' access capacity by up to 500% during adversarial load. $PD^3F$ represents a step toward the resilient and resource-aware deployment of LLMs against resource consumption attacks.

Related papers

• PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models [50.232333672172395]
  Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency.<n>We propose textbfPolicyTrim, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps.<n>Our framework delivers up to a 5.83$times$ end-to-end deployment speedup without compromising task success rates.
  arXiv  Detail & Related papers  (2026-06-21T14:54:07Z)
• Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models [22.44538447178147]
  Adrial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets.<n>We propose a compute-aware evaluation framework based on computational pressure, measured in cumulative floating-point operations.
  arXiv  Detail & Related papers  (2026-06-09T19:59:12Z)
• RECALLED: An Unbounded Resource Consumption Attack on Large Vision-Language Models [16.62034667623657]
  Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs)<n>We present RECALLED, the first approach for exploiting visual modalities to trigger RCAs red-teaming.<n>Our study exposes security vulnerabilities in LVLMs and establishes a red-teaming framework that can facilitate future defense development against RCAs.
  arXiv  Detail & Related papers  (2025-07-24T02:58:16Z)
• Sampling-aware Adversarial Attacks Against Large Language Models [52.30089653615172]
  Existing adversarial attacks typically target harmful responses in single-point greedy generations.<n>We show that for the goal of eliciting harmful responses, repeated sampling of model outputs during the attack prompt optimization.<n>We show that integrating sampling into existing attacks boosts success rates by up to 37% and improves efficiency by up to two orders of magnitude.
  arXiv  Detail & Related papers  (2025-07-06T16:13:33Z)
• ExtendAttack: Attacking Servers of LRMs via Extending Reasoning [27.205747119390846]
  Large Reasoning Models (LRMs) have demonstrated promising performance in complex tasks.<n>We propose a novel attack method on LRMs termed ExtendAttack to maliciously occupy the resources of servers.<n>We show that ExtendAttack increases the length of the model's response by over 2.5 times for the o3 model on the HumanEval benchmark.
  arXiv  Detail & Related papers  (2025-06-16T17:49:05Z)
• Capability-Based Scaling Laws for LLM Red-Teaming [71.89259138609965]
  Traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem.<n>We evaluate more than 500 attacker-target pairs using LLM-based jailbreak attacks that mimic human red-teamers.<n>We derive a jailbreaking scaling law that predicts attack success for a fixed target based on attacker-target capability gap.
  arXiv  Detail & Related papers  (2025-05-26T16:05:41Z)
• Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training [50.829723203044395]
  We propose $textitAdversary-aware DPO (ADPO)$, a novel training framework that explicitly considers adversarial.<n>$textitADPO$ integrates adversarial training into DPO to enhance the safety alignment of VLMs under worst-case adversarial perturbations.<n>$textitADPO$ ensures that VLMs remain robust and reliable even in the presence of sophisticated jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-17T05:28:47Z)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [63.603861880022954]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability.<n>Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.<n>It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models [8.024771725860127]
  Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. We introduce a novel scalable jailbreak attack that preempts the activation of an LLM's safety policies by occupying its computational resources.
  arXiv  Detail & Related papers  (2024-10-05T15:10:01Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)
• Multi-Level ML Based Burst-Aware Autoscaling for SLO Assurance and Cost Efficiency [3.5624365288866007]
  This paper introduces BAScaler, a Burst-Aware Autoscaling framework for containerized cloud services or applications under complex workloads. BAScaler incorporates a novel prediction-based burst detection mechanism that distinguishes between predictable periodic workload spikes and actual bursts.
  arXiv  Detail & Related papers  (2024-02-20T12:28:25Z)
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning [50.9692060692705]
  This paper introduces $textbfLanguage Models for $textbfMo$tion Control ($textbfLaMo$), a general framework based on Decision Transformers for offline RL.<n>Our framework highlights four crucial components:.<n>Initializing Decision Transformers with sequentially pre-trained LMs, (2) employing the LoRA fine-tuning method,.<n>In particular, our method demonstrates superior performance in scenarios with limited data samples.
  arXiv  Detail & Related papers  (2023-10-31T16:24:17Z)
• Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks [67.86285142381644]
  Recent advances in instruction-following large language models amplify the dual-use risks for malicious purposes. Dual-use is difficult to prevent as instruction-following capabilities now enable standard attacks from computer security. We show that instruction-following LLMs can produce targeted malicious content, including hate speech and scams.
  arXiv  Detail & Related papers  (2023-02-11T15:57:44Z)
• ReLeaSER: A Reinforcement Learning Strategy for Optimizing Utilization Of Ephemeral Cloud Resources [2.205500582481277]
  We propose a Reinforcement Learning strategy for optimizing the ephemeral resources' utilization in the cloud. Our solution reduces significantly the SLA violation penalties on average by 2.7x and up to 3.4x. It also improves considerably the CPs' potential savings by 27.6% on average and up to 43.6%.
  arXiv  Detail & Related papers  (2020-09-23T15:19:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.