arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2105.01403cs.CRcs.AI
收藏

嵌入式神经网络模型的激光注入研究综述

An Overview of Laser Injection against Embedded Neural Network Models

CEA Tech(法国原子能委员会技术部);Mines Saint-Etienne(圣艾蒂安矿业学院);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学)

Mathieu Dumont, Pierre-Alain Moellic, Raphael Viera, Jean-Max Dutertre, Rémi Bernhard

摘要:

对于许多物联网领域,机器学习,尤其是深度学习带来了非常有效的解决方案,可以处理复杂的数据,并执行具有挑战性的关键任务。然而,在各种各样的设备中部署模型面临着与信任和安全性相关的几个障碍。最新的是特别关键的,因为严重的缺陷影响了神经网络模型的完整性,机密性和可访问性的演示。然而,这种嵌入式系统的攻击表面不能被简化为抽象的缺陷,而是必须包括与在硬件平台内实现这些模型相关的物理威胁(例如,32-位微控制器)。在物理攻击中,故障注入分析(FIA)被认为是非常强大的攻击向量。最重要的是,高度聚焦的FIA技术(如激光束注入)可以非常准确地评估嵌入式系统的脆弱性和鲁棒性。在这里,我们建议讨论如何使用最先进的设备进行激光注入,结合对抗性机器学习的理论证据,突出了对深度学习推理完整性的令人担忧的威胁,并声称迫切需要理论AI和物理安全社区的共同努力。

英文摘要:

For many IoT domains, Machine Learning and more particularly Deep Learning brings very efficient solutions to handle complex data and perform challenging and mostly critical tasks. However, the deployment of models in a large variety of devices faces several obstacles related to trust and security. The latest is particularly critical since the demonstrations of severe flaws impacting the integrity, confidentiality and accessibility of neural network models. However, the attack surface of such embedded systems cannot be reduced to abstract flaws but must encompass the physical threats related to the implementation of these models within hardware platforms (e.g., 32-bit microcontrollers). Among physical attacks, Fault Injection Analysis (FIA) are known to be very powerful with a large spectrum of attack vectors. Most importantly, highly focused FIA techniques such as laser beam injection enable very accurate evaluation of the vulnerabilities as well as the robustness of embedded systems. Here, we propose to discuss how laser injection with state-of-the-art equipment, combined with theoretical evidences from Adversarial Machine Learning, highlights worrying threats against the integrity of deep learning inference and claims that join efforts from the theoretical AI and Physical Security communities are a urgent need.

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。

↑