Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Preprint
Abstract
Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are normally formulated with two separate stages, where a directional guide is required to be determined at first and the scalar projection of the intermediate-level perturbation onto the directional guide is enlarged thereafter. The obtained perturbation deviates from the guide inevitably in the feature space, and it is revealed in this paper that such a deviation may lead to sub-optimal attack. To address this issue, we develop a novel intermediate-level method that crafts adversarial examples within a single stage of optimization. In particular, the proposed method, named intermediate-level perturbation decay (ILPD), encourages the intermediate-level perturbation to be in an effective adversarial direction and to possess a great magnitude simultaneously. In-depth discussion verifies the effectiveness of our method. Experimental results show that it outperforms state-of-the-arts by large margins in attacking various victim models on ImageNet (+10.07% on average) and CIFAR-10 (+3.88% on average). Our code is at https://github.com/qizhangli/ILPD-attack.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- An Intermediate-level Attack Framework on The Basis of Linear RegressionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- HopSkipJumpAttack: A Query-Efficient Decision-Based Attack2020
- Enhancing Adversarial Example Transferability With an Intermediate Level Attack2019
- Searching for a Robust Neural Architecture in Four GPU Hours2019
- Improving Transferability of Adversarial Examples With Input Diversity2019
- Boosting Adversarial Attacks with Momentum2018
- Deep Pyramidal Residual Networks2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016