Robustness of Large Language Models Against Adversarial Attacks

2024/12/22 by Yiyi Tao, Tao, Yiyi, Yixian Shen +11 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2412.17011

openalex publication_date 2024/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT LLM family. We employ two distinct evaluation methods to assess their resilience. The first method introduce character-level text attack in input prompts, testing the models on three sentiment classification datasets: StanfordNLP/IMDB, Yelp Reviews, and SST-2. The second method involves using jailbreak prompts to challenge the safety mechanisms of the LLMs. Our experiments reveal significant variations in the robustness of these models, demonstrating their varying degrees of vulnerability to both character-level and semantic-level adversarial attacks. These findings underscore the necessity for improved adversarial training and enhanced safety mechanisms to bolster the robustness of LLMs.

Cited by

• Understanding the Ability of LLMs to Handle Character-Level Perturbation
• LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

Related

• Assessing Adversarial Robustness of Large Language Models: An Empirical Study
• Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
• Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
• Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts
• Adversarial Evasion Attack Efficiency against Large Language Models