Assessing Adversarial Robustness of Large Language Models: An Empirical Study

2024/05/04 by Zeyu Yang, Yang, Zeyu, Zhao Meng +5 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning

paper · pdf · doi:10.48550/arxiv.2405.02764

Abstract

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in leading open-source LLMs, including Llama, OPT, and T5. We assess the impact of model size, structure, and fine-tuning strategies on their resistance to adversarial perturbations. Our comprehensive evaluation across five diverse text classification tasks establishes a new benchmark for LLM robustness. The findings of this study have far-reaching implications for the reliable deployment of LLMs in real-world applications and contribute to the advancement of trustworthy AI systems.

Cited by

• Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks
• Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox
• Uncovering Competency Gaps in Large Language Models and Their Benchmarks
• Robustness as an Emergent Property of Task Performance
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol
• Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

Related

• Robustness of Large Language Models Against Adversarial Attacks
• Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
• Adversarial Evasion Attack Efficiency against Large Language Models
• Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
• A LLM Assisted Exploitation of AI-Guardian