arXiv:1704.02654

Enhancing Robustness of Machine Learning Systems via Data Transformations

Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, Prateek Mittal

제출 2017-04-09

원문 초록

We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduction via Principal Component Analysis and data `anti-whitening' to enhance the resilience of machine learning, targeting both the classification and the training phase. We empirically evaluate and demonstrate the feasibility of linear transformations of data as a defense mechanism against evasion attacks using multiple real-world datasets. Our key findings are that the defense is (i) effective against the best known evasion attacks from the literature, resulting in a two-fold increase in the resources required by a white-box adversary with knowledge of the defense for a successful attack, (ii) applicable across a range of ML classifiers, including Support Vector Machines and Deep Neural Networks, and (iii) generalizable to multiple application domains, including image classification and human activity classification.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

논문 ID: document/9197689공통 태그 Dimensionality Reduction, Classification, Image Classification

Fuzzy Pooling

토론

이 논문과 연결된 포럼 글이 아직 없습니다.