Sitatapatra: Blocking the Transfer of Adversarial Samples
Shumailov, Ilia, Gao, Xitong, Zhao, Yiren, Mullins, Robert, Anderson, Ross, Xu, Cheng-Zhong
Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision. However, they can be tricked into misclassifying specially crafted `adversarial' samples -- and samples built to trick one model often work alarmingly well against other models trained on the same task. In this paper we introduce Sitatapatra, a system designed to block the transfer of adversarial samples. It diversifies neural networks using a key, as in cryptography, and provides a mechanism for detecting attacks. What's more, when adversarial samples are detected they can typically be traced back to the individual device that was used to develop them. The run-time overheads are minimal permitting the use of Sitatapatra on constrained systems.
Jan-23-2019
- Country:
- Asia > China (0.14)
- North America > United States (0.14)
- Genre:
- Research Report (0.64)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: