English
Related papers

Related papers: Constrained Adversarial Perturbation

200 papers

Interpreting neural network classifiers using gradient-based saliency maps has been extensively studied in the deep learning literature. While the existing algorithms manage to achieve satisfactory performance in application to standard…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Haniyeh Ehsani Oskouie , Farzan Farnia

We introduce Universal and Transferable Adversarial Perturbations (UTAP) for pathology foundation models that reveal critical vulnerabilities in their capabilities. Optimized using deep learning, UTAP comprises a fixed and weak noise…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Yuntian Wang , Xilin Yang , Che-Yung Shen , Nir Pillar , Aydogan Ozcan

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

Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To…

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

Neural models of code have shown impressive results when performing tasks such as predicting method names and identifying certain kinds of bugs. We show that these models are vulnerable to adversarial examples, and introduce a novel…

Machine Learning · Computer Science 2020-10-14 Noam Yefet , Uri Alon , Eran Yahav

Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels. In contrast, a universal perturbation is an update that can be added to any image in a broad…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Ali Shafahi , Mahyar Najibi , Zheng Xu , John Dickerson , Larry S. Davis , Tom Goldstein

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Machine Learning · Computer Science 2022-05-20 Thomas Cilloni , Charles Walter , Charles Fleming

Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Hanieh Naderi , Leili Goli , Shohreh Kasaei

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Machine Learning · Computer Science 2018-01-16 Bo Luo , Yannan Liu , Lingxiao Wei , Qiang Xu

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

Recently, with the application of deep learning in the remote sensing image (RSI) field, the classification accuracy of the RSI has been dramatically improved compared with traditional technology. However, even the state-of-the-art object…

Computer Vision and Pattern Recognition · Computer Science 2023-01-04 Qingyu Wang , Guorui Feng , Zhaoxia Yin , Bin Luo

When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks…

Machine Learning · Computer Science 2019-02-21 Kaidi Xu , Sijia Liu , Pu Zhao , Pin-Yu Chen , Huan Zhang , Quanfu Fan , Deniz Erdogmus , Yanzhi Wang , Xue Lin

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN…

Cryptography and Security · Computer Science 2022-05-10 Zirui Peng , Shaofeng Li , Guoxing Chen , Cheng Zhang , Haojin Zhu , Minhui Xue

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Fan Yang , Mingxuan Xia , Sangzhou Xia , Chicheng Ma , Hui Hui

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…

Cryptography and Security · Computer Science 2025-06-12 Hetvi Waghela , Jaydip Sen , Sneha Rakshit , Subhasis Dasgupta

Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, CNN models have been found vulnerable to universal adversarial perturbations (UAPs),…

Machine Learning · Computer Science 2022-11-15 Zihan Liu , Lubin Meng , Xiao Zhang , Weili Fang , Dongrui Wu

Machine learning algorithms have been shown to be vulnerable to adversarial manipulation through systematic modification of inputs (e.g., adversarial examples) in domains such as image recognition. Under the default threat model, the…

Cryptography and Security · Computer Science 2022-09-12 Ryan Sheatsley , Nicolas Papernot , Michael Weisman , Gunjan Verma , Patrick McDaniel

Deep learning-based person re-identification (Re-ID) has made great progress and achieved high performance recently. In this paper, we make the first attempt to examine the vulnerability of current person Re-ID models against a dangerous…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Wenjie Ding , Xing Wei , Rongrong Ji , Xiaopeng Hong , Qi Tian , Yihong Gong

Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial…

Computer Vision and Pattern Recognition · Computer Science 2024-05-12 Peng-Fei Zhang , Zi Huang , Guangdong Bai