Transferable Clean-Label Poisoning Attacks on Deep Neural Nets

Authors: Chen Zhu, W. Ronny Huang, Ali Shafahi, Hengduo Li, Gavin Taylor, Christoph Studer, Tom Goldstein
Published: 2019-05-15 | Updated: 2019-05-16

Source: https://arxiv.org/abs/1905.05897

PDF: https://arxiv.org/pdf/1905.05897

AIにより推定されたラベル

攻撃タイプ バックドア攻撃 ポイズニング

※ 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

Clean-label poisoning attacks inject innocuous looking (and “correctly” labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network’s outputs, architecture, or (in some cases) training data. To achieve this, we propose a new “polytope attack” in which poison images are designed to surround the targeted image in feature space. We also demonstrate that using Dropout during poison creation helps to enhance transferability of this attack. We achieve transferable attack success rates of over 50 training set.