DeepAI AI Chat
Log In Sign Up

Towards Robust Image Classification Using Sequential Attention Models

12/04/2019
by   Daniel Zoran, et al.
Google
11

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention component that is guided by a recurrent top-down sequential process. Our experimental evaluation uncovers several notable findings about the robustness and behavior of this new model. First, introducing attention to the model significantly improves adversarial robustness resulting in state-of-the-art ImageNet accuracies under a wide range of random targeted attack strengths. Second, we show that by varying the number of attention steps (glances/fixations) for which the model is unrolled, we are able to make its defense capabilities stronger, even in light of stronger attacks — resulting in a "computational race" between the attacker and the defender. Finally, we show that some of the adversarial examples generated by attacking our model are quite different from conventional adversarial examples — they contain global, salient and spatially coherent structures coming from the target class that would be recognizable even to a human, and work by distracting the attention of the model away from the main object in the original image.

READ FULL TEXT

page 1

page 8

page 14

page 15

11/25/2019

One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples

Modern image classification systems are often built on deep neural netwo...
03/13/2021

Internal Wasserstein Distance for Adversarial Attack and Defense

Deep neural networks (DNNs) are vulnerable to adversarial examples that ...
08/31/2018

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

Despite being popularly used in many application domains such as image r...
08/18/2022

Enhancing Targeted Attack Transferability via Diversified Weight Pruning

Malicious attackers can generate targeted adversarial examples by imposi...
03/11/2018

Detecting Adversarial Examples via Neural Fingerprinting

Deep neural networks are vulnerable to adversarial examples, which drama...
09/14/2022

Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models

Neural ranking models (NRMs) have achieved promising results in informat...
08/31/2019

Knowledge Enhanced Attention for Robust Natural Language Inference

Neural network models have been very successful at achieving high accura...