DeepLaser: Practical Fault Attack on Deep Neural Networks

Autor:	Breier, Jakub, Hou, Xiaolu, Jap, Dirmanto, Ma, Lei, Bhasin, Shivam, Liu, Yang
Rok vydání:	2018
Předmět:	Computer Science - Cryptography and Security Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a tremendous concern, which potentially could lead to catastrophic consequences. In this paper, we initiate the first study of leveraging physical fault injection attacks on Deep Neural Networks (DNNs), by using laser injection technique on embedded systems. In particular, our exploratory study targets four widely used activation functions in DNNs development, that are the general main building block of DNNs that creates non-linear behaviors -- ReLu, softmax, sigmoid, and tanh. Our results show that by targeting these functions, it is possible to achieve a misclassification by injecting faults into the hidden layer of the network. Such result can have practical implications for real-world applications, where faults can be introduced by simpler means (such as altering the supply voltage). Comment: 11 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1806.05859 Zobrazit plný text záznamu View this record from Arxiv