NETWORK ROBUSTNESS TO PCA PERTURBATIONS

2021-01-01 · Anan Kabaha, Dana Drachsler Cohen

A key challenge in analyzing neural networks' robustness is identifying input features for which networks are robust to perturbations. Existing work focuses on direct perturbations to the inputs, thereby studies network robustness to the lowest-level features. In this work, we take a new approach and study the robustness of networks to the inputs' semantic features. We show a black-box approach to determine features for which a network is robust or weak. We leverage these features to obtain provably robust neighborhoods defined using robust features and adversarial examples defined by perturbing weak features. We evaluate our approach with PCA features. We show (1) provably robust neighborhoods are larger: on average by 1.8x and up to 4.5x, compared to the standard neighborhoods, and (2) our adversarial examples are generated using at least 8.7x fewer queries and have at least 2.8x lower L2 distortion compared to state-of-the-art. We further show that our attack is effective even against ensemble adversarial training.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?

2019-09-04 · Alfred Laugros, Alice Caplier, Matthieu Ospici

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adv…

Adversarial Robustness

Universality, Robustness, and Detectability of Adversarial Perturbations under Adversarial Training

2018-01-01 · ICLR 2018 1 · Jan Hendrik Metzen

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of classifiers…

Adversarial and Natural Perturbations for General Robustness

2020-10-03 · Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness …

Evaluating Robustness to Input Perturbations for Neural Machine Translation

2020-05-01 · ACL 2020 6 · Xing Niu, Prashant Mathur, Georgiana Dinu, Yaser Al-Onaizan

Neural Machine Translation (NMT) models are sensitive to small perturbations in the input. Robustness to such perturbations is typically measured using translation quality metrics such as BLEU on the noisy input. This pa…

Machine Translation NMT Translation

Robustness of classifiers to universal perturbations: a geometric perspective

2017-05-26 · ICLR 2018 1 · Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard 외

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this pape…