arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00476cs.CRcs.LG
收藏

SCNet:一种用于自动侧信道攻击的神经网络

SCNet: A Neural Network for Automated Side-Channel Attack

Shandong Computer Science Center(山东省计算中心);Nanyang Technological University(南洋理工大学);Shandong University(山东大学);Tsinghua University(清华大学);Open Security Research Company(开放安全研究公司)

Guanlin Li, Chang Liu, Han Yu, Yanhong Fan, Libang Zhang, Zongyue Wang, Meiqin Wang

摘要:

侧信道攻击是基于所获得的关于计算机系统的实现的信息而不是算法中的弱点的攻击方法。侧信道攻击可以利用关于系统特性的信息,例如功耗、电磁泄漏和声音,来危害系统。许多研究工作都是针对这一领域的。不过,这种攻击需要很强的技巧,只有高手才能有效地进行。在这里,我们提出了SCNet,它自动执行侧信道攻击。并结合侧通道领域知识和不同的深度学习模型设计了该网络,以提高性能,更好地解释结果。结果表明,我们的模型取得了良好的性能与较少的参数。该模型为计算机系统的鲁棒性自动测试提供了一种有效的工具。

英文摘要:

The side-channel attack is an attack method based on the information gained about implementations of computer systems, rather than weaknesses in algorithms. Information about system characteristics such as power consumption, electromagnetic leaks and sound can be exploited by the side-channel attack to compromise the system. Much research effort has been directed towards this field. However, such an attack still requires strong skills, thus can only be performed effectively by experts. Here, we propose SCNet, which automatically performs side-channel attacks. And we also design this network combining with side-channel domain knowledge and different deep learning model to improve the performance and better to explain the result. The results show that our model achieves good performance with fewer parameters. The proposed model is a useful tool for automatically testing the robustness of computer systems.

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。

↑