Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Zeyu, Meng, Zhao, Zheng, Xiaochen, Wattenhofer, Roger
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.02764
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917774877523968
author Yang, Zeyu
Meng, Zhao
Zheng, Xiaochen
Wattenhofer, Roger
author_facet Yang, Zeyu
Meng, Zhao
Zheng, Xiaochen
Wattenhofer, Roger
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02764
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Assessing Adversarial Robustness of Large Language Models: An Empirical Study
Yang, Zeyu
Meng, Zhao
Zheng, Xiaochen
Wattenhofer, Roger
Computation and Language
Machine Learning
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.
title Assessing Adversarial Robustness of Large Language Models: An Empirical Study
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.02764