paper-with-me

Papers

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 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.

📄 PDF Abstract BibTeX arXiv:2304.13410

Code (2)

qizhangli/ilpd-attack 공식 구현 pytorch
Trustworthy-AI-Group/TransferAttack pytorch

Similar Papers 제목 키워드 기반

Enhancing Adversarial Example Transferability with an Intermediate Level Attack

2019-07-23 · ICCV 2019 10 · Qian Huang, Isay Katsman, Horace He, Zeqi Gu 외

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool ano…

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

2021-08-16 · Ruikui Wang, Yuanfang Guo, Ruijie Yang, Yunhong Wang

The transferability and robustness of adversarial examples are two practical yet important properties for black-box adversarial attacks. In this paper, we explore effective mechanisms to boost both of them from the persp…

Diversity

Intermediate Level Adversarial Attack for Enhanced Transferability

2018-11-20 · Qian Huang, Zeqi Gu, Isay Katsman, Horace He 외

Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool ano…

Adversarial Attack

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 f…

Adversarial AttackImage Augmentation

Semantic Structure-Aware Generative Attacks for Enhanced Adversarial Transferability

2025-06-23 · Jongoh Jeong, Hunmin Yang, Jaeseok Jeong, Kuk-Jin Yoon

Generative adversarial attacks train a perturbation generator on a white-box surrogate model and subsequently apply the crafted perturbations to unseen black-box victim models. In contrast to iterative attacks, these met…