Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References

2021-09-29 · Chiu Wai Yan, Dit-yan Yeung

An intriguing property of deep neural networks is that adversarial attacks can transfer across different models. Existing methods such as the Intermediate Level Attack (ILA) further improve black-box transferability by fine-tuning a reference adversarial attack, so as to maximize the perturbation on a pre-specified layer of the source model. In this paper, we revisit ILA and evaluate the effect of applying augmentation to the images before passing them to ILA. We start by looking into the effect of common image augmentation techniques and exploring novel augmentation with the aid of adversarial perturbations. Based on the observations, we propose Aug-ILA, an improved method that enhances the transferability of an existing attack under the ILA framework. Specifically, Aug-ILA has three main characteristics: typical image augmentation such as random cropping and resizing applied to all ILA inputs, reverse adversarial update on the clean image, and interpolation between two attacks on the reference image. Our experimental results show that Aug-ILA outperforms ILA and its subsequent variants, as well as state-of-the-art transfer-based attacks, by achieving $96.99\%$ and $87.84\%$ average attack success rates with perturbation budgets $0.05$ and $0.03$, respectively, on nine undefended models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack Image Augmentation

Learning Transferable Adversarial Perturbations

2021-12-01 · NeurIPS 2021 12 · Krishna Kanth Nakka, Mathieu Salzmann

While effective, deep neural networks (DNNs) are vulnerable to adversarial attacks. In particular, recent work has shown that such attacks could be generated by another deep network, leading to significant speedups over …

Brain Tumor Classifiers Under Attack: Robustness of ResNet Variants Against Transferable FGSM and PGD Attacks

2026-02-12 · Ryan Deem, Garrett Goodman, Waqas Majeed, Md Abdullah Al Hafiz Khan 외 arxiv

Adversarial robustness in deep learning models for brain tumor classification remains an underexplored yet critical challenge, particularly for clinical deployment scenarios involving MRI data. In this work, we investiga…

Brain Tumor Classification Adversarial Robustness

Improving Adversarial Transferability via Neuron Attribution-Based Attacks

2022-03-31 · CVPR 2022 1 · Jianping Zhang, Weibin Wu, Jen-tse Huang, Yizhan Huang 외

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs beforehand in security-sensitive applicatio…

Attribute

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

2023-04-26 · NeurIPS 2023 11 · Qizhang Li, Yiwen Guo, WangMeng Zuo, Hao Chen

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 i…

Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning

2025-07-09 · Giulio Rossolini, Fabio Brau, Alessandro Biondi, Battista Biggio 외 arxiv

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a …