paper-with-me

Papers

Decision-based Universal Adversarial Attack

2020-09-15 · Jing Wu, Mingyi Zhou, Shuaicheng Liu, Yipeng Liu, Ce Zhu

A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute models to generate the perturbation, then apply the perturbation to the attacked model. However, this transfer often produces inferior results. In this study, we directly work in the black-box setting to generate the universal adversarial perturbation. Besides, we aim to design an adversary generating a single perturbation having texture like stripes based on orthogonal matrix, as the top convolutional layers are sensitive to stripes. To this end, we propose an efficient Decision-based Universal Attack (DUAttack). With few data, the proposed adversary computes the perturbation based solely on the final inferred labels, but good transferability has been realized not only across models but also span different vision tasks. The effectiveness of DUAttack is validated through comparisons with other state-of-the-art attacks. The efficiency of DUAttack is also demonstrated on real world settings including the Microsoft Azure. In addition, several representative defense methods are struggling with DUAttack, indicating the practicability of the proposed method.

📄 PDF Abstract BibTeX arXiv:2009.07024

Code (1)

JoeyW221/DUAttack 공식 구현 pytorch

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Universalization of any adversarial attack using very few test examples

2020-05-18 · Sandesh Kamath, Amit Deshpande, K V Subrahmanyam, Vineeth N Balasubramanian

Deep learning models are known to be vulnerable not only to input-dependent adversarial attacks but also to input-agnostic or universal adversarial attacks. Dezfooli et al. \cite{Dezfooli17,Dezfooli17anal} construct univ…

Adversarial Attack

Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient Estimation

2023-03-09 · Geunhyeok Yu, Minwoo Jeon, Hyoseok Hwang

The susceptibility of deep neural networks (DNNs) to adversarial examples has prompted an increase in the deployment of adversarial attacks. Image-agnostic universal adversarial perturbations (UAPs) are much more threate…

Adversarial Attack

TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems

2021-11-19 · Bao Gia Doan, Minhui Xue, Shiqing Ma, Ehsan Abbasnejad 외

Deep neural networks are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the model's decision. We expose the existence of an intriguing class of spatially bounded, physical…

Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning

2022-11-15 · Yiran Huang, Yexu Zhou, Michael Hefenbrock, Till Riedel 외

The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine …

Adversarial Attackreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Universal Adversarial Audio Perturbations

2019-08-08 · arXiv preprint 2019 11 · Sajjad Abdoli, Luiz G. Hafemann, Jerome Rony, Ismail Ben Ayed 외

We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding su…

Audio Classification