Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks

Authors: Alex Habeen Chang, Benjamin M. Case
Published: 2020-04-28 | Updated: 2020-04-29

Source: https://arxiv.org/abs/2004.13263

PDF: https://arxiv.org/pdf/2004.13263

AIにより推定されたラベル

アルゴリズム 暗号化手法 攻撃パターン抽出

※ 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

Privacy preserving machine learning is an active area of research usually relying on techniques such as homomorphic encryption or secure multiparty computation. Recent novel encryption techniques for performing machine learning using deep neural nets on images have recently been proposed by Tanaka and Sirichotedumrong, Kinoshita, and Kiya. We present new chosen-plaintext and ciphertext-only attacks against both of these proposed image encryption schemes and demonstrate the attacks’ effectiveness on several examples.