Yet Another Intermediate-Level Attack

08/20/2020
by   Qizhang Li, et al.
3

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial examples. By establishing a linear mapping of the intermediate-level discrepancies (between a set of adversarial inputs and their benign counterparts) for predicting the evoked adversarial loss, we aim to take full advantage of the optimization procedure of multi-step baseline attacks. We conducted extensive experiments to verify the effectiveness of our method on CIFAR-100 and ImageNet. Experimental results demonstrate that it outperforms previous state-of-the-arts considerably. Our code is at https://github.com/qizhangli/ila-plus-plus.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/20/2018

Intermediate Level Adversarial Attack for Enhanced Transferability

Neural networks are vulnerable to adversarial examples, malicious inputs...
12/07/2020

Backpropagating Linearly Improves Transferability of Adversarial Examples

The vulnerability of deep neural networks (DNNs) to adversarial examples...
03/21/2022

An Intermediate-level Attack Framework on The Basis of Linear Regression

This paper substantially extends our work published at ECCV, in which an...
05/26/2022

Transferable Adversarial Attack based on Integrated Gradients

The vulnerability of deep neural networks to adversarial examples has dr...
07/12/2022

Frequency Domain Model Augmentation for Adversarial Attack

For black-box attacks, the gap between the substitute model and the vict...
06/14/2020

On the transferability of adversarial examples between convex and 01 loss models

We show that white box adversarial examples do not transfer effectively ...
04/20/2021

Staircase Sign Method for Boosting Adversarial Attacks

Crafting adversarial examples for the transfer-based attack is challengi...