A Unified Approach to Interpreting and Boosting Adversarial Transferability

10/08/2020
by   Xin Wang, et al.
0

In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations. The negative correlation is further verified through different DNNs with various inputs. Moreover, this negative correlation can be regarded as a unified perspective to understand current transferability-boosting methods. To this end, we prove that some classic methods of enhancing the transferability essentially decease interactions inside adversarial perturbations. Based on this, we propose to directly penalize interactions during the attacking process, which significantly improves the adversarial transferability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/24/2022

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

Although many methods have been proposed to enhance the transferability ...
research
06/14/2023

Reliable Evaluation of Adversarial Transferability

Adversarial examples (AEs) with small adversarial perturbations can misl...
research
08/16/2021

Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchy

The transferability and robustness of adversarial examples are two pract...
research
06/09/2022

Early Transferability of Adversarial Examples in Deep Neural Networks

This paper will describe and analyze a new phenomenon that was not known...
research
08/11/2022

Diverse Generative Adversarial Perturbations on Attention Space for Transferable Adversarial Attacks

Adversarial attacks with improved transferability - the ability of an ad...
research
11/05/2021

A Unified Game-Theoretic Interpretation of Adversarial Robustness

This paper provides a unified view to explain different adversarial atta...
research
04/26/2021

Impact of Spatial Frequency Based Constraints on Adversarial Robustness

Adversarial examples mainly exploit changes to input pixels to which hum...

Please sign up or login with your details

Forgot password? Click here to reset