Resource Consumption Threats in Large Language Models

2026-03-16

AI Summary

Large language models are vulnerable to resource-consuming attacks—such as those maliciously inducing excessive generation—which jeopardize service availability and economic sustainability. This work presents the first systematic survey of this emerging threat class, introducing a unified analytical framework that encompasses threat elicitation, operational mechanisms, and mitigation strategies. Through a comprehensive literature review integrated with threat modeling, efficiency analysis, and categorization of defense mechanisms, the study clearly delineates the problem boundaries and maps the research landscape. The resulting synthesis establishes a foundational theoretical basis and outlines a coherent research agenda for future efforts in threat characterization, detection, and defense.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Large language models for search
• Security and Privacy: Large-scale security measurements

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.

Problem

• resource consumption
• large language models
• efficiency
• service availability
• economic sustainability

Innovation

• resource consumption threats
• large language models
• systematic review
• unified framework
• efficiency degradation