Recent Advances in Attack and Defense Approaches of Large Language Models

2024/09/05 by Jing Cui, Cui, Jing, Yihua Xu +8 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Network Security and Intrusion Detection #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2409.03274

openalex publication_date 2024/09/05 · openalex created_date 2024/10/21 · openalex updated_date 2026/07/28

Abstract

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and reliability concerns. Established vulnerabilities in deep neural networks, coupled with emerging threat models, may compromise security evaluations and create a false sense of security. Given the extensive research in the field of LLM security, we believe that summarizing the current state of affairs will help the research community better understand the present landscape and inform future developments. This paper reviews current research on LLM vulnerabilities and threats, and evaluates the effectiveness of contemporary defense mechanisms. We analyze recent studies on attack vectors and model weaknesses, providing insights into attack mechanisms and the evolving threat landscape. We also examine current defense strategies, highlighting their strengths and limitations. By contrasting advancements in attack and defense methodologies, we identify research gaps and propose future directions to enhance LLM security. Our goal is to advance the understanding of LLM safety challenges and guide the development of more robust security measures.

Cited by

• TrajSyn: Privacy-Preserving Dataset Distillation from Federated Model Trajectories for Server-Side Adversarial Training
• SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
• DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems
• LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

Related

• Attack and defense techniques in large language models: A survey and new perspectives
• Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
• A Comprehensive Survey of Attack Techniques, Implementation, and Mitigation Strategies in Large Language Models
• Security Concerns for Large Language Models: A Survey
• Emerging Security Challenges of Large Language Models