论文标题
通过功耗信息增强对基于NVM NVM的基于NVM横杆的神经网络的对抗性攻击
Enhancing Adversarial Attacks on Single-Layer NVM Crossbar-Based Neural Networks with Power Consumption Information
论文作者
论文摘要
对最先进的机器学习模型的对抗性攻击对关键任务自治系统的安全和安全构成了重大威胁。当攻击者可以衡量其基础硬件平台的功耗时，本文考虑了机器学习模型的其他脆弱性。特别是，我们探讨了对非易失性记忆横杆单层神经网络对对抗性攻击的功耗信息的实用性。我们对使用MNIST和CIFAR-10数据集实验的结果表明，功耗可以揭示有关神经网络的重量矩阵的重要信息，例如其列的1核。该信息可用于推断网络损失相对于不同输入的敏感性。我们还发现，利用横杆力量信息的基于替代物的黑匣子攻击可以提高攻击效率。
Adversarial attacks on state-of-the-art machine learning models pose a significant threat to the safety and security of mission-critical autonomous systems. This paper considers the additional vulnerability of machine learning models when attackers can measure the power consumption of their underlying hardware platform. In particular, we explore the utility of power consumption information for adversarial attacks on non-volatile memory crossbar-based single-layer neural networks. Our results from experiments with MNIST and CIFAR-10 datasets show that power consumption can reveal important information about the neural network's weight matrix, such as the 1-norm of its columns. That information can be used to infer the sensitivity of the network's loss with respect to different inputs. We also find that surrogate-based black box attacks that utilize crossbar power information can lead to improved attack efficiency.
