Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions

Authors: Michael Goebel, Jason Bunk, Srinjoy Chattopadhyay, Lakshmanan Nataraj, Shivkumar Chandrasekaran, B. S. Manjunath
Published: 2021-03-19

Source: https://arxiv.org/abs/2103.11002

PDF: https://arxiv.org/pdf/2103.11002

AIにより推定されたラベル

敵対的攻撃手法 ポイズニング データ抽出と分析

※ 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

Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in recovering the tools and processes used in these attacks. In this paper, we present two techniques that support automated identification and attribution of adversarial ML attack toolchains using Co-occurrence Pixel statistics and Laplacian Residuals. Our experiments show that the proposed techniques can identify parameters used to generate adversarial samples. To the best of our knowledge, this is the first approach to attribute gradient based adversarial attacks and estimate their parameters. Source code and data is available at: https://github.com/michael-goebel/ei_red