Keyed Non-Parametric Hypothesis Tests

Authors: Yao Cheng, Cheng-Kang Chu, Hsiao-Ying Lin, Marius Lombard-Platet, David Naccache
Published: 2020-05-25

Source: https://arxiv.org/abs/2005.12227

PDF: https://arxiv.org/pdf/2005.12227

AIにより推定されたラベル

ポイズニング 敵対的攻撃 機械学習技術

※ 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

The recent popularity of machine learning calls for a deeper understanding of AI security. Amongst the numerous AI threats published so far, poisoning attacks currently attract considerable attention. In a poisoning attack the opponent partially tampers the dataset used for learning to mislead the classifier during the testing phase. This paper proposes a new protection strategy against poisoning attacks. The technique relies on a new primitive called keyed non-parametric hypothesis tests allowing to evaluate under adversarial conditions the training input’s conformance with a previously learned distribution 𝔇. To do so we use a secret key κ unknown to the opponent. Keyed non-parametric hypothesis tests differs from classical tests in that the secrecy of κ prevents the opponent from misleading the keyed test into concluding that a (significantly) tampered dataset belongs to 𝔇.