arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07183cs.CRcs.AIcs.CV
收藏

深度学习中的神经木马攻击与防御综述

A Survey of Neural Trojan Attacks and Defenses in Deep Learning

Jie Wang, Ghulam Mubashar Hassan, Naveed Akhtar

摘要:

人工智能(AI)在很大程度上依赖于深度学习--这种技术在AI的实际应用中越来越受欢迎,即使在安全关键和高风险领域也是如此。然而,最近发现深度学习可以通过在其中嵌入木马来操纵。不幸的是,规避深度学习计算要求的实用解决方案,例如将模型训练或数据注释外包给第三方,进一步增加了模型对木马攻击的敏感性。由于该主题在深度学习中的关键重要性,最近的文献在这个方向上做出了许多贡献。我们对为深度学习设计特洛伊木马攻击的技术进行了全面的回顾,并探讨了它们的防御措施。我们的信息调查系统地组织了最近的文献,并讨论了方法的关键概念,同时假设读者对该领域的知识最少。它为更广泛的社区提供了一个可理解的门户,以了解神经特洛伊木马的最新发展。

英文摘要:

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that deep learning can be manipulated by embedding Trojans inside it. Unfortunately, pragmatic solutions to circumvent the computational requirements of deep learning, e.g. outsourcing model training or data annotation to third parties, further add to model susceptibility to the Trojan attacks. Due to the key importance of the topic in deep learning, recent literature has seen many contributions in this direction. We conduct a comprehensive review of the techniques that devise Trojan attacks for deep learning and explore their defenses. Our informative survey systematically organizes the recent literature and discusses the key concepts of the methods while assuming minimal knowledge of the domain on the readers part. It provides a comprehensible gateway to the broader community to understand the recent developments in Neural Trojans.

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。

↑