Scholarlink

<p>Deep neural networks (DNNs) are highly sensitive to small, meticulously crafted perturbations, which have been utilized in adversarial attacks, threatening the reliability of DNNs in practical applications. Current adversarial attack methods rely heavily on expert design, requiring significant researcher effort. In this paper, we introduce LLM-GA, a Large Language Model-based Gradient Attack method, specifically designed for generating adversarial attacks against multi-label classification models. Based on the prompts and algorithm templates provided by attackers, LLM-GA can automatically generate ideas for attack algorithms and produce corresponding code implementations. This significantly improves the efficiency of designing adversarial attack algorithms. To generate more effective attack algorithms, LLM-GA leverages evolutionary algorithms to iteratively refine its ideas. Experimental results demonstrate that LLM-GA outperforms three existing gradient-based adversarial attacks in terms of both attack success rate and perturbation size. The code for this paper is available <a href="https://github.com/liuyujiang123/LLM-GA">https://github.com/liuyujiang123/LLM-GA</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Llm-ga: A gradient-based multi-label adversarial attack by large language models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月12日

查看全文
  • Yujiang Liu,
  • Yamin Hu,
  • Zhijian Chen,
  • Shiyin Wang,
  • Wenjian Luo

摘要

Deep neural networks (DNNs) are highly sensitive to small, meticulously crafted perturbations, which have been utilized in adversarial attacks, threatening the reliability of DNNs in practical applications. Current adversarial attack methods rely heavily on expert design, requiring significant researcher effort. In this paper, we introduce LLM-GA, a Large Language Model-based Gradient Attack method, specifically designed for generating adversarial attacks against multi-label classification models. Based on the prompts and algorithm templates provided by attackers, LLM-GA can automatically generate ideas for attack algorithms and produce corresponding code implementations. This significantly improves the efficiency of designing adversarial attack algorithms. To generate more effective attack algorithms, LLM-GA leverages evolutionary algorithms to iteratively refine its ideas. Experimental results demonstrate that LLM-GA outperforms three existing gradient-based adversarial attacks in terms of both attack success rate and perturbation size. The code for this paper is available https://github.com/liuyujiang123/LLM-GA.