Paper deep dive
Security Threats in the Inference Phase of Large Language Models
Baolin Yan, Xiaotian Ai, Yuxi Ma, Lingzhong Meng, Guang Yang
Intelligence
Status: succeeded | Model: google/gemini-3.1-flash-lite-preview | Prompt: intel-v1 | Confidence: 91%
Last extracted: 3/11/2026, 1:12:56 AM
Summary
This paper provides a systematic analysis of security vulnerabilities in the inference phase of Large Language Models (LLMs), proposing a taxonomy of risk factors including logical inconsistencies, linguistic disruptions, and cognitive biases that impact high-stakes applications.
Entities (4)
Relation Signals (3)
Large Language Models → exhibits → Security Vulnerabilities
confidence 95% · unveiled a spectrum of critical security vulnerabilities
Security Vulnerabilities → affects → Inference Phase
confidence 90% · systematic analysis of security threats arising during the inference phase
Large Language Models → usedin → Decision Support Systems
confidence 85% · posing significant risks to high-stakes applications such as decision support systems
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
In recent years, Large Language Models (LLMs) have achieved remarkable advancements in natural language understanding, contextual modeling, and human-like reasoning. However, these capabilities have also unveiled a spectrum of critical security vulnerabilities, including logical inconsistencies during inference, linguistic and semantic disruptions, and entrenched cognitive biases. Such deficiencies can cause LLMs to produce inaccurate, misleading, or even harmful outputs, posing significant risks to high-stakes applications such as decision support systems, legal consultation, and medical diagnostics. This paper presents a systematic analysis of security threats arising during the inference phase of LLMs. By examining the inference pipeline across its distinct stages and the varying levels of abstraction at which threats manifest, we propose a comprehensive taxonomy of potential security risk factors. Furthermore, we conduct targeted testing and validation to assess the impact of these threats. Our study aims to provide both theoretical insights and practical guidance for the development and deployment of safer and more reliable LLM systems.
Tags
Links
Full Text
813 characters extracted from source content.
Expand or collapse full text
Security Threats in the Inference Phase of Large Language Models | IEEE Conference Publication | IEEE Xplore IEEE Account Change Username/Password Update Address Purchase Details Payment Options Order History View Purchased Documents Profile Information Communications Preferences Profession and Education Technical Interests Need Help? US & Canada: +1 800 678 4333 Worldwide: +1 732 981 0060 Contact & Support About IEEE Xplore Contact Us Help Accessibility Terms of Use Nondiscrimination Policy Sitemap Privacy & Opting Out of Cookies A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2026 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.