paper-with-me

홈 › Papers

Generative Adversarial Perturbations

2017-12-06 · CVPR 2018 6 · Omid Poursaeed, Isay Katsman, Bicheng Gao, Serge Belongie

In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for both targeted and non-targeted attacks. We also demonstrate that similar architectures can achieve impressive results in fooling classification and semantic segmentation models, obviating the need for hand-crafting attack methods for each task. Using extensive experiments on challenging high-resolution datasets such as ImageNet and Cityscapes, we show that our perturbations achieve high fooling rates with small perturbation norms. Moreover, our attacks are considerably faster than current iterative methods at inference time.

📄 PDF Abstract BibTeX arXiv:1712.02328

Code (1)

OmidPoursaeed/Generative_Adversarial_Perturbations 공식 구현 pytorch

Tasks

General ClassificationSemantic Segmentation

Similar Papers 제목 키워드 기반

A Little Fog for a Large Turn

2020-01-16 · Harshitha Machiraju, Vineeth N. Balasubramanian

Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Au…

Adversarial AttackAutonomous NavigationSafety Perception Recognition

Adversarial vulnerability for any classifier

2018-02-23 · NeurIPS 2018 12 · Alhussein Fawzi, Hamza Fawzi, Omar Fawzi

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to addres…

General Classification

Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbations

2021-08-22 · Inci M. Baytas, Debayan Deb

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversari…

Diversity

Learning Universal Adversarial Perturbations with Generative Models

2017-08-17 · Jamie Hayes, George Danezis

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that …

Graph Classification

Metrics and methods for robustness evaluation of neural networks with generative models

2020-03-04 · Igor Buzhinsky, Arseny Nerinovsky, Stavros Tripakis

Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and meth…

Adversarial Robustnessimage-classificationImage Classification