paper-with-me

Papers

Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution

2025-03-06 · Yihao Huang, Xin Luo, Qing Guo, Felix Juefei-Xu, Xiaojun Jia, Weikai Miao, Geguang Pu, Yang Liu

The advent of local continuous image function (LIIF) has garnered significant attention for arbitrary-scale super-resolution (SR) techniques. However, while the vulnerabilities of fixed-scale SR have been assessed, the robustness of continuous representation-based arbitrary-scale SR against adversarial attacks remains an area warranting further exploration. The elaborately designed adversarial attacks for fixed-scale SR are scale-dependent, which will cause time-consuming and memory-consuming problems when applied to arbitrary-scale SR. To address this concern, we propose a simple yet effective ``scale-invariant'' SR adversarial attack method with good transferability, termed SIAGT. Specifically, we propose to construct resource-saving attacks by exploiting finite discrete points of continuous representation. In addition, we formulate a coordinate-dependent loss to enhance the cross-model transferability of the attack. The attack can significantly deteriorate the SR images while introducing imperceptible distortion to the targeted low-resolution (LR) images. Experiments carried out on three popular LIIF-based SR approaches and four classical SR datasets show remarkable attack performance and transferability of SIAGT.

📄 PDF Abstract BibTeX arXiv:2503.04385

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackSuper-Resolution

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

2022-01-29 · Mengting Xu, Tao Zhang, Zhongnian Li, Daoqiang Zhang

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adver…

Adversarial AttackAdversarial Defense

Augmenting Model Robustness with Transformation-Invariant Attacks

2019-01-31 · Houpu Yao, Zhe Wang, GuangYu Nie, Yassine Mazboudi 외

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensiti…

Image CroppingmodelTranslation

Towards Defending against Adversarial Examples via Attack-Invariant Features

2021-06-09 · Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang 외

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen t…

Adversarial Robustness

ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation

2021-01-01 · Dawei Zhou, Tongliang Liu, Bo Han, Nannan Wang 외

Due to vulnerability of machine learning algorithms under adversarial examples, it is challenging to defend against them. Recently, various defenses have been proposed to mitigate negative effects of adversarial examples…

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