Security Concerns for Large Language Models: A Survey

TL;DR

This survey reviews emerging security vulnerabilities in Large Language Models, categorizing threats like inference, training, misuse, and autonomous agents, and discusses defense mechanisms and future challenges.

Contribution

It provides a comprehensive overview of security concerns in LLMs, analyzing recent studies, threats, defenses, and open challenges in the field.

Findings

Identification of key threat categories in LLM security

Analysis of current defense mechanisms and their limitations

Highlighting open challenges for future research

Abstract

Large Language Models (LLMs) such as ChatGPT and its competitors have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. This survey provides a comprehensive overview of these emerging concerns, categorizing threats into several key areas: inference-time attacks via prompt manipulation; training-time attacks; misuse by malicious actors; and the inherent risks in autonomous LLM agents. Recently, a significant focus is increasingly being placed on the latter. We summarize recent academic and industrial studies from 2022 to 2025 that exemplify each threat, analyze existing defense mechanisms and their limitations, and identify open challenges in securing LLM-based applications. We conclude by emphasizing the importance of advancing robust, multi-layered security strategies to ensure LLMs are safe and beneficial.