arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.03363cs.LGcs.AIcs.CR
收藏

对抗性机器学习阅读综述:对抗性攻击及其理解

A reading survey on adversarial machine learning: Adversarial attacks and their understanding

Kyushu University(九州大学)

Shashank Kotyan

AI总结:

本文综述了对抗性机器学习中的对抗性攻击分类与理解,并概述现有防御方法的局限性,为该领域未来研究方向提供参考。

摘要:

深度学习使我们能够针对复杂数据训练高性能的神经网络。然而,随着研究的不断深入,神经网络中的若干脆弱性已被暴露出来。一个特定的研究分支——对抗性机器学习(Adversarial Machine Learning)——利用并理解其中一些会导致神经网络对接近原始输入的样本产生错误分类的脆弱性。一类被称为对抗性攻击(adversarial attacks)的算法被提出,用于使神经网络在不同领域的各种任务中发生错误分类。随着对抗性攻击研究的广泛开展和不断增长,理解对抗性攻击的分类至关重要。这将有助于我们以系统化的顺序理解这些脆弱性,并帮助我们减轻对抗性攻击的影响。本文基于不同视角对现有对抗性攻击及其理解进行了综述。我们还简要概述了现有的对抗性防御(adversarial defences)及其在减轻对抗性攻击影响方面的局限性。此外,我们在结论部分讨论了对抗性机器学习领域未来的研究方向。

英文摘要:

Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of research, Adversarial Machine Learning, exploits and understands some of the vulnerabilities that cause the neural networks to misclassify for near original input. A class of algorithms called adversarial attacks is proposed to make the neural networks misclassify for various tasks in different domains. With the extensive and growing research in adversarial attacks, it is crucial to understand the classification of adversarial attacks. This will help us understand the vulnerabilities in a systematic order and help us to mitigate the effects of adversarial attacks. This article provides a survey of existing adversarial attacks and their understanding based on different perspectives. We also provide a brief overview of existing adversarial defences and their limitations in mitigating the effect of adversarial attacks. Further, we conclude with a discussion on the future research directions in the field of adversarial machine learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑