Resource Consumption Threats in Large Language Models

• URL: http://arxiv.org/abs/2603.16068v2
• Date: Wed, 18 Mar 2026 01:51:39 GMT
• Title: Resource Consumption Threats in Large Language Models
• Abstract summary: Resource efficiency is a key requirement for large language models (LLMs)<n>Recent resource consumption threats induce excessive generation, degrading model efficiency and harming service availability and economic sustainability.<n>Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.
• Score: 18.038172925174642
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent resource consumption threats induce excessive generation, degrading model efficiency and harming both service availability and economic sustainability. This survey presents a systematic review of threats to resource consumption in LLMs. We further establish a unified view of this emerging area by clarifying its scope and examining the problem along the full pipeline from threat induction to mechanism understanding and mitigation. Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.

Related papers

• Task-Aware Reduction for Scalable LLM-Database Systems [0.0]
  We argue for treating the token budget of an LLM as an attention budget and elevating task-aware text reduction as a first-class design principle for language -- data systems.<n>We outline open research challenges for building benchmarks, designing adaptive reduction pipelines, and integrating token-budget-aware preprocessing into database and retrieval systems.
  arXiv  Detail & Related papers  (2025-10-13T18:10:03Z)
• $PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models [9.585089414738542]
  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.
  arXiv  Detail & Related papers  (2025-05-24T12:54:22Z)
• Network Resource Optimization for ML-Based UAV Condition Monitoring with Vibration Analysis [54.550658461477106]
  Condition Monitoring (CM) uses Machine Learning (ML) models to identify abnormal and adverse conditions.<n>This work explores the optimization of network resources for ML-based UAV CM frameworks.<n>By leveraging dimensionality reduction techniques, there is a 99.9% reduction in network resource consumption.
  arXiv  Detail & Related papers  (2025-02-21T14:36:12Z)
• Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting [2.023914201416672]
  We introduce DisasTeller, the first multi-LVLM-powered framework designed to automate tasks in post-disaster management. DisasTeller autonomously implements disaster response activities, reducing human execution time and optimising resource distribution.
  arXiv  Detail & Related papers  (2024-11-03T10:25:55Z)
• Large Language Models can be Strong Self-Detoxifiers [82.6594169242814]
  Self-disciplined Autoregressive Sampling (SASA) is a lightweight controlled decoding algorithm for toxicity reduction of large language models (LLMs) SASA tracks the margin of the current output to steer the generation away from the toxic subspace, by adjusting the autoregressive sampling strategy. evaluated on LLMs of different scale and nature, namely Llama-3.1-Instruct (8B), Llama-2 (7B), and GPT2-L models with the RealToxicityPrompts, BOLD, and AttaQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-04T17:45:15Z)
• Enhancing Supply Chain Visibility with Knowledge Graphs and Large Language Models [49.898152180805454]
  This paper presents a novel framework leveraging Knowledge Graphs (KGs) and Large Language Models (LLMs) to enhance supply chain visibility. Our zero-shot, LLM-driven approach automates the extraction of supply chain information from diverse public sources. With high accuracy in NER and RE tasks, it provides an effective tool for understanding complex, multi-tiered supply networks.
  arXiv  Detail & Related papers  (2024-08-05T17:11:29Z)
• ORIENT: A Priority-Aware Energy-Efficient Approach for Latency-Sensitive Applications in 6G [15.753216159980434]
  Growing concerns about increased energy consumption in computing and networking. The expected surge in connected devices and resource-demanding applications presents unprecedented challenges for energy resources. We investigate the joint problem of service instance placement and assignment, path selection, and request prioritization, dubbed PIRA.
  arXiv  Detail & Related papers  (2024-02-10T12:05:52Z)
• Proactive Resource Request for Disaster Response: A Deep Learning-based Optimization Model [0.2580765958706854]
  We develop a new resource management problem that proactively decides optimal quantities of requested resources. We take salient characteristics of the problem into consideration and develop a novel deep learning method for future demand prediction. We demonstrate the superior performance of our method over prevalent existing methods using both real world and simulated data.
  arXiv  Detail & Related papers  (2023-07-31T13:44:01Z)
• On the Risk of Misinformation Pollution with Large Language Models [127.1107824751703]
  We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation in the performance of Open-Domain Question Answering (ODQA) systems.
  arXiv  Detail & Related papers  (2023-05-23T04:10:26Z)
• Coordinated Online Learning for Multi-Agent Systems with Coupled Constraints and Perturbed Utility Observations [91.02019381927236]
  We introduce a novel method to steer the agents toward a stable population state, fulfilling the given resource constraints. The proposed method is a decentralized resource pricing method based on the resource loads resulting from the augmentation of the game's Lagrangian.
  arXiv  Detail & Related papers  (2020-10-21T10:11:17Z)
• Risk-Aware Energy Scheduling for Edge Computing with Microgrid: A Multi-Agent Deep Reinforcement Learning Approach [82.6692222294594]
  We study a risk-aware energy scheduling problem for a microgrid-powered MEC network. We derive the solution by applying a multi-agent deep reinforcement learning (MADRL)-based advantage actor-critic (A3C) algorithm with shared neural networks.
  arXiv  Detail & Related papers  (2020-02-21T02:14:38Z)

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.