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 2110.11290cs.CRcs.LGcs.NE
收藏

嵌入式神经网络的物理侧信道攻击综述

Physical Side-Channel Attacks on Embedded Neural Networks: A Survey

Univ Nantes(南特大学);CNRS(法国国家科学研究中心)

Maria Méndez Real, Rubén Salvador

摘要:

在过去的十年中,深度神经网络(DNN)已逐步集成到所有类型的平台上,从数据中心到嵌入式系统,包括低功耗处理器,最近又集成到FPGA。神经网络(NN)有望在物联网系统中无处不在,它可以改变各种现实世界的应用,包括安全关键和安全敏感领域的应用。然而,嵌入式NN实现的底层硬件安全漏洞仍然没有得到解决。特别是,嵌入式DNN实现容易受到侧信道分析(SCA)攻击,这在物联网和边缘计算环境中尤为重要,攻击者通常可以获得对目标设备的物理访问。因此,出现了一个研究领域,并在使用SCA方面迅速发展,包括定时,电磁攻击和功率攻击,以针对NN嵌入式实现。自2018年以来,研究论文表明,SCA使攻击者能够恢复推理模型架构和参数,暴露工业IP并危及数据机密性和隐私。到目前为止,在文献中没有对这一新兴领域进行完整的回顾,本文调查了与微控制器和FPGA上嵌入式DNN的实现相关的最先进的物理SCA攻击,以便对当前形势进行全面分析。它提供了当前攻击的分类和详细分类。它首先讨论了缓解技术,然后为未来的研究提供了见解。

英文摘要:

During the last decade, Deep Neural Networks (DNN) have progressively been integrated on all types of platforms, from data centers to embedded systems including low-power processors and, recently, FPGAs. Neural Networks (NN) are expected to become ubiquitous in IoT systems by transforming all sorts of real-world applications, including applications in the safety-critical and security-sensitive domains. However, the underlying hardware security vulnerabilities of embedded NN implementations remain unaddressed. In particular, embedded DNN implementations are vulnerable to Side-Channel Analysis (SCA) attacks, which are especially important in the IoT and edge computing contexts where an attacker can usually gain physical access to the targeted device. A research field has therefore emerged and is rapidly growing in terms of the use of SCA including timing, electromagnetic attacks and power attacks to target NN embedded implementations. Since 2018, research papers have shown that SCA enables an attacker to recover inference models architectures and parameters, to expose industrial IP and endangers data confidentiality and privacy. Without a complete review of this emerging field in the literature so far, this paper surveys state-of-the-art physical SCA attacks relative to the implementation of embedded DNNs on micro-controllers and FPGAs in order to provide a thorough analysis on the current landscape. It provides a taxonomy and a detailed classification of current attacks. It first discusses mitigation techniques and then provides insights for future research leads.

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。

↑