English
Related papers

Related papers: On the Universal Adversarial Perturbations for Eff…

200 papers

Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbations (UAP) that can affect inference of the models over most…

Computer Vision and Pattern Recognition · Computer Science 2018-08-06 Konda Reddy Mopuri , Phani Krishna Uppala , R. Venkatesh Babu

Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input…

Cryptography and Security · Computer Science 2022-02-03 Raphael Labaca-Castro , Luis Muñoz-González , Feargus Pendlebury , Gabi Dreo Rodosek , Fabio Pierazzi , Lorenzo Cavallaro

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…

Machine Learning · Computer Science 2023-06-27 Vyas Raina , Mark Gales

This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb…

Probability · Mathematics 2024-10-28 Gleb Smirnov

We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by comparing the discrete vector fields they follow through the…

Machine Learning · Computer Science 2023-06-09 Skander Karkar , Patrick Gallinari , Alain Rakotomamonjy

Deep neural networks (DNN) have been shown to be useful in a wide range of applications. However, they are also known to be vulnerable to adversarial samples. By transforming a normal sample with some carefully crafted human imperceptible…

Machine Learning · Computer Science 2019-11-22 Jingyi Wang , Guoliang Dong , Jun Sun , Xinyu Wang , Peixin Zhang

Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks. Thus far, efforts mostly focused on generating adversarial…

Computation and Language · Computer Science 2023-01-26 Luoqiu Li , Xiang Chen , Zhen Bi , Xin Xie , Shumin Deng , Ningyu Zhang , Chuanqi Tan , Mosha Chen , Huajun Chen

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such…

Computer Vision and Pattern Recognition · Computer Science 2019-08-14 Chaithanya Kumar Mummadi , Thomas Brox , Jan Hendrik Metzen

Deep neural networks tend to be vulnerable to adversarial perturbations, which by adding to a natural image can fool a respective model with high confidence. Recently, the existence of image-agnostic perturbations, also known as universal…

Computer Vision and Pattern Recognition · Computer Science 2020-10-30 Atiye Sadat Hashemi , Andreas Bär , Saeed Mozaffari , Tim Fingscheidt

The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain…

Sound · Computer Science 2025-11-26 Wangjie Li , Lin Li , Qingyang Hong

Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs). These perturbations are meticulously designed to fool the target model universally across all sample classes. Unlike instance-specific adversarial…

Machine Learning · Computer Science 2025-04-17 Yechao Zhang , Yingzhe Xu , Junyu Shi , Leo Yu Zhang , Shengshan Hu , Minghui Li , Yanjun Zhang

We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generated by projected gradient descent exhibit two human-aligned…

Machine Learning · Computer Science 2022-01-03 Sung Min Park , Kuo-An Wei , Kai Xiao , Jerry Li , Aleksander Madry

Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data. They are a class of attacks that represents a significant threat as they facilitate realistic, practical, and low-cost…

Machine Learning · Computer Science 2021-09-14 Kenneth T. Co , David Martinez Rego , Emil C. Lupu

Deep neural networks have achieved remarkable success in a wide range of classification tasks. However, they remain highly susceptible to adversarial examples - inputs that are subtly perturbed to induce misclassification while appearing…

Machine Learning · Computer Science 2025-10-20 Virendra Nishad , Bhaskar Mukhoty , Hilal AlQuabeh , Sandeep K. Shukla , Sayak Ray Chowdhury

Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking…

Computer Vision and Pattern Recognition · Computer Science 2019-09-12 Jie Li , Rongrong Ji , Hong Liu , Xiaopeng Hong , Yue Gao , Qi Tian

Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such models are dangerously susceptible to adversarial samples,…

Machine Learning · Computer Science 2017-11-21 Lovedeep Gondara

Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the…

Cryptography and Security · Computer Science 2024-08-06 Liang-bo Ning , Zeyu Dai , Wenqi Fan , Jingran Su , Chao Pan , Luning Wang , Qing Li

Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs) which are maliciously designed to fool target models. The normal examples (NEs) added with imperceptible adversarial perturbation, can be a…

Computer Vision and Pattern Recognition · Computer Science 2022-08-31 Mingyu Dong , Jiahao Chen , Diqun Yan , Jingxing Gao , Li Dong , Rangding Wang

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…

Machine Learning · Statistics 2017-08-02 Jan Hendrik Metzen , Mummadi Chaithanya Kumar , Thomas Brox , Volker Fischer

Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Eylon Mizrahi , Raz Lapid , Moshe Sipper