Sitatapatra: Blocking the Transfer of Adversarial Samples

Authors: Ilia Shumailov, Xitong Gao, Yiren Zhao, Robert Mullins, Ross Anderson, Cheng-Zhong Xu
Published: 2019-01-23 | Updated: 2019-11-21

Source: https://arxiv.org/abs/1901.08121

PDF: https://arxiv.org/pdf/1901.08121

AIにより推定されたラベル

敵対的サンプル モデルの頑健性保証 非転送性検出

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

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.