Practical Approaches Toward Deep-Learning-Based Cross-Device Power Side-Channel Attack
Practical Approaches Toward Deep-Learning-Based Cross-Device Power Side-Channel Attack
复制标题
DOI：
10.1109/tvlsi.2019.2926324
复制
发表时间：
2019-12-01
影响因子：
2.8
通讯作者：
Raychowdhury, Arijit
中科院分区：
文献类型：
--
作者：
Golder, Anupam;Das, Debayan;Raychowdhury, Arijit
电源侧信道分析（SCA）是大多数嵌入式设计人员用来评估系统物理安全性的重要手段。这项工作提出了基于分析的跨设备电源SCA攻击，使用深度学习技术对运行AES-128的8位AVR微控制器设备进行攻击。首先，我们展示了这些基于分析的跨设备攻击中由于设备到设备的显著变化而出现的实际问题。第二，我们表明，利用主成分分析（PCA）为基础的预处理和多设备训练，多层感知器（MLP）为基础的256类分类器可以实现99.43%的平均准确率恢复第一个关键字节从所有30个设备在我们的数据集中，即使在存在显着的设备间的变化。结果表明，所设计的基于PCA预处理的MLP在使用ChipWhisperer硬件捕获的对齐痕迹的跨设备攻击的平均测试准确度方面，优于具有四个设备训练的卷积神经网络（CNN），接近20%。最后，为了扩展这些跨设备攻击的实用性，另一个预处理步骤，即，动态时间规整（DTW）已被用来消除任何不对齐的痕迹，在执行PCA之前。DTW沿着PCA之后是256类MLP分类器，即使在迹线之间存在多达50个时间样本未对准的情况下，也比基于CNN的跨设备攻击方法提供了>= 10.97%的高准确度。
Power side-channel analysis (SCA) has been of immense interest to most embedded designers to evaluate the physical security of the system. This work presents profilingbased cross-device power SCA attacks using deep-learning techniques on 8-bit AVR microcontroller devices running AES-128. First, we show the practical issues that arise in these profiling-based cross-device attacks due to significant device-to-device variations. Second, we show that utilizing principal component analysis (PCA)-based preprocessing and multidevice training, a multilayer perceptron (MLP)-based 256-class classifier can achieve an average accuracy of 99.43% in recovering the first keybyte from all the 30 devices in our data set, even in the presence of significant interdevice variations. Results show that the designed MLP with PCA-based preprocessing outperforms a convolutional neural network (CNN) with four-device training by similar to 20% in terms of the average test accuracy of cross-device attack for the aligned traces captured using the ChipWhisperer hardware. Finally, to extend the practicality of these crossdevice attacks, another preprocessing step, namely, dynamic time warping (DTW) has been utilized to remove any misalignment among the traces, before performing PCA. DTW along with PCA followed by the 256-class MLP classifier provides >= 10.97% higher accuracy than the CNN-based approach for cross-device attack even in the presence of up to 50 time-sample misalignments between the traces.