paper-with-me

Papers

Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path

2024-12-25 · Yuchen Ren, Zhengyu Zhao, Chenhao Lin, Bo Yang, Lu Zhou, Zhe Liu, Chao Shen

Transferable adversarial examples are known to cause threats in practical, black-box attack scenarios. A notable approach to improving transferability is using integrated gradients (IG), originally developed for model interpretability. In this paper, we find that existing IG-based attacks have limited transferability due to their naive adoption of IG in model interpretability. To address this limitation, we focus on the IG integration path and refine it in three aspects: multiplicity, monotonicity, and diversity, supported by theoretical analyses. We propose the Multiple Monotonic Diversified Integrated Gradients (MuMoDIG) attack, which can generate highly transferable adversarial examples on different CNN and ViT models and defenses. Experiments validate that MuMoDIG outperforms the latest IG-based attack by up to 37.3\% and other state-of-the-art attacks by 8.4\%. In general, our study reveals that migrating established techniques to improve transferability may require non-trivial efforts. Code is available at \url{https://github.com/RYC-98/MuMoDIG}.

📄 PDF Abstract BibTeX arXiv:2412.18844

Code (1)

ryc-98/mumodig 공식 구현 pytorch

Tasks

Diversity

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Transferable Adversarial Attack based on Integrated Gradients

2022-05-26 · ICLR 2022 4 · Yi Huang, Adams Wai-Kin Kong

The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community. Three approaches, optimizing standard objective functions, exploiting attention maps, and smoothing dec…

Adversarial Attack

Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients

2023-01-01 · ICCV 2023 1 · Wenshuo Ma, Yidong Li, Xiaofeng Jia, Wei Xu

Visual Transformers (ViTs) and Convolutional Neural Networks (CNNs) are the two primary backbone structures extensively used in various vision tasks. Generating transferable adversarial examples for ViTs is difficult…

Adversarial Attack

Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks

2019-08-17 · ICLR 2020 1 · Jiadong Lin, Chuanbiao Song, Kun He, Li-Wei Wang 외

Deep learning models are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on benign inputs. However, under the black-box setting, most existing adversaries often have a poor transf…

Adversarial Attack

Adversarial example generation with AdaBelief Optimizer and Crop Invariance

2021-02-07 · Bo Yang, Hengwei Zhang, Yuchen Zhang, Kaiyong Xu 외

Deep neural networks are vulnerable to adversarial examples, which are crafted by applying small, human-imperceptible perturbations on the original images, so as to mislead deep neural networks to output inaccurate predi…

Towards Transferable Targeted Attack

2020-06-01 · CVPR 2020 6 · Maosen Li, Cheng Deng, Tengjiao Li, Junchi Yan 외

An intriguing property of adversarial examples is their transferability, which suggests that black-box attacks are feasible in real-world applications. Previous works mostly study the transferability on non-targeted sett…

Metric Learning