Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Taro Kiritani, Koji Ono
2/13/2020
cs.CV

No confident code implementation found for this paper.

Abstract

Convolutional neural networks are vulnerable to small $\ell^p$ adversarial attacks, while the human visual system is not. Inspired by neural networks in the eye and the brain, we developed a novel artificial neural network model that recurrently collects data with a log-polar field of view that is controlled by attention. We demonstrate the effectiveness of this design as a defense against SPSA and PGD adversarial attacks. It also has beneficial properties observed in the animal visual system, such as reflex-like pathways for low-latency inference, fixed amount of computation independent of image size, and rotation and scale invariance. The code for experiments is available at https://gitlab.com/exwzd-public/kiritani_ono_2020.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications

88% match2023

Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks

86% match2023

I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors

86% match1 repo122024

On Inherent Adversarial Robustness of Active Vision Systems

85% match2024

A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges

85% match2025

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

85% match1 repo62024

Cite this paper

@article{kiritani2020recurrent,
  title  = {Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks},
  author = {Taro Kiritani and Koji Ono},
  year   = {2020},
  eprint = {2002.05388},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2002.05388}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2002.05388.svg)](https://codeofpaper.com/paper/2002.05388)

Discussion