Yet Another Intermediate-Level Attack

by   Qizhang Li, et al.

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


page 1

page 2

page 3

page 4


Intermediate Level Adversarial Attack for Enhanced Transferability

Neural networks are vulnerable to adversarial examples, malicious inputs...

Backpropagating Linearly Improves Transferability of Adversarial Examples

The vulnerability of deep neural networks (DNNs) to adversarial examples...

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

This paper substantially extends our work published at ECCV, in which an...

Transferable Adversarial Attack based on Integrated Gradients

The vulnerability of deep neural networks to adversarial examples has dr...

Frequency Domain Model Augmentation for Adversarial Attack

For black-box attacks, the gap between the substitute model and the vict...

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

We show that white box adversarial examples do not transfer effectively ...

Staircase Sign Method for Boosting Adversarial Attacks

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