paper-with-me

Papers

Content-based Unrestricted Adversarial Attack

2023-05-18 · NeurIPS 2023 11

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. However, current works usually sacrifice unrestricted degrees and subjectively select some image content to guarantee the photorealism of unrestricted adversarial examples, which limits its attack performance. To ensure the photorealism of adversarial examples and boost attack performance, we propose a novel unrestricted attack framework called Content-based Unrestricted Adversarial Attack. By leveraging a low-dimensional manifold that represents natural images, we map the images onto the manifold and optimize them along its adversarial direction. Therefore, within this framework, we implement Adversarial Content Attack based on Stable Diffusion and can generate high transferable unrestricted adversarial examples with various adversarial contents. Extensive experimentation and visualization demonstrate the efficacy of ACA, particularly in surpassing state-of-the-art attacks by an average of 13.3-50.4% and 16.8-48.0% in normally trained models and defense methods, respectively.

📄 PDF Abstract BibTeX arXiv:2305.10665

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

ColorFool: Semantic Adversarial Colorization

2019-11-25 · CVPR 2020 6 · Ali Shahin Shamsabadi, Ricardo Sanchez-Matilla, Andrea Cavallaro

Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoisi…

Adversarial AttackColorizationDenoising

Adaptive Generation of Unrestricted Adversarial Inputs

2019-05-07 · Isaac Dunn, Hadrien Pouget, Tom Melham, Daniel Kroening

Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is …

SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion

2024-10-03 · Zihao Pan, Lifeng Chen, Weibin Wu, Yuhang Cao 외

Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples …

Adversarial AttackDenoisingLanguage ModellingLarge Language Model+1

Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries

2022-08-24 · Dongbin Na, Sangwoo Ji, Jong Kim

Adversarial examples are inputs intentionally generated for fooling a deep neural network. Recent studies have proposed unrestricted adversarial attacks that are not norm-constrained. However, the previous unrestricted a…

Adversarial AttackClassification

Unrestricted Adversarial Attacks on ImageNet Competition

2021-10-17 · Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue 외

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to compl…

Adversarial Attack