Assessing Adversarial Robustness of Large Language Models: An Empirical Study
This addresses the critical concern of reliable deployment of LLMs in real-world applications for AI practitioners and researchers.
The paper tackles the problem of adversarial robustness in large language models by developing a novel white-box attack approach that exposes vulnerabilities in leading open-source LLMs like Llama, OPT, and T5, establishing a new benchmark across five text classification tasks.
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.