arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.14243cs.CRcs.LG
收藏

深入研究评估针对深度神经网络的位翻转攻击

A Closer Look at Evaluating the Bit-Flip Attack Against Deep Neural Networks

CEA Tech(法国原子能和替代能源委员会技术研究院);Mines Saint-Etienne(圣埃蒂安矿业学院);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学)

Kevin Hector, Mathieu Dumont, Pierre-Alain Moellic, Jean-Max Dutertre

摘要:

深度神经网络模型被大规模部署在各种硬件平台上。这导致出现新的攻击向量,显著扩展了标准攻击面,对抗性机器学习社区对此进行了广泛研究。第一种攻击旨在通过针对存储在内存中的模型参数(权重)来大幅降低模型的性能,这就是位翻转攻击(BFA)。在这项工作中,我们指出了与博鳌亚洲论坛有关的几个评估挑战。首先,在标准威胁模型中缺乏对手的预算是有问题的,特别是在处理物理攻击时。此外,由于BFA提出了关键的可变性,我们讨论了一些训练参数的影响和模型架构的重要性。这项工作首次展示了BFA对全连接架构的影响,与卷积神经网络相比,全连接架构呈现不同的行为。这些结果强调了定义强大和合理的评估方法的重要性,以正确评估基于参数的攻击的危险,以及衡量防御提供的鲁棒性的真实水平。

英文摘要:

Deep neural network models are massively deployed on a wide variety of hardware platforms. This results in the appearance of new attack vectors that significantly extend the standard attack surface, extensively studied by the adversarial machine learning community. One of the first attack that aims at drastically dropping the performance of a model, by targeting its parameters (weights) stored in memory, is the Bit-Flip Attack (BFA). In this work, we point out several evaluation challenges related to the BFA. First of all, the lack of an adversary's budget in the standard threat model is problematic, especially when dealing with physical attacks. Moreover, since the BFA presents critical variability, we discuss the influence of some training parameters and the importance of the model architecture. This work is the first to present the impact of the BFA against fully-connected architectures that present different behaviors compared to convolutional neural networks. These results highlight the importance of defining robust and sound evaluation methodologies to properly evaluate the dangers of parameter-based attacks as well as measure the real level of robustness offered by a defense.

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。

↑