English
Related papers

Related papers: Certified Zeroth-order Black-Box Defense with Robu…

200 papers

Deep Neural Network (DNN) based classifiers have recently been used for the modulation classification of RF signals. These classifiers have shown impressive performance gains relative to conventional methods, however, they are vulnerable to…

Machine Learning · Computer Science 2024-10-10 Wenhan Zhang , Meiyu Zhong , Ravi Tandon , Marwan Krunz

It has been well recognized that neural network based image classifiers are easily fooled by images with tiny perturbations crafted by an adversary. There has been a vast volume of research to generate and defend such adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Yifan Gong , Yuguang Yao , Yize Li , Yimeng Zhang , Xiaoming Liu , Xue Lin , Sijia Liu

Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Xuelong Dai , Dong Wang , Xiuzhen Cheng , Bin Xiao

Introduction: Deep learning-based segmentation models are increasingly integrated into clinical imaging workflows, yet their robustness to adversarial perturbations remains incompletely characterized, particularly for ultrasound images. We…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Nicholas Dietrich , David McShannon

In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous works, here we focus on the white-box adversarial defense where…

Machine Learning · Computer Science 2019-09-16 Zudi Lin , Hanspeter Pfister , Ziming Zhang

Low Dose Computed Tomography (LDCT) has offered tremendous benefits in radiation restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance. Current…

Computer Vision and Pattern Recognition · Computer Science 2019-03-06 Xin Yi , Paul Babyn

Deep Neural Networks (DNNs) are vulnerable to backdoor attacks. Due to the nature of Machine Learning as a Service (MLaaS) applications, black-box defenses are more practical than white-box methods, yet existing purification techniques…

Cryptography and Security · Computer Science 2026-03-31 Abdullah Arafat Miah , Yu Bi

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model in a "white box" setting and to the opposite in a "black box" setting. In this…

Machine Learning · Computer Science 2021-07-09 Daniel Park , Haidar Khan , Azer Khan , Alex Gittens , Bülent Yener

Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work…

Machine Learning · Computer Science 2020-01-28 Rehana Mahfuz , Rajeev Sahay , Aly El Gamal

The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in the development of deep learning. Although new deep learning…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Chang Liu , Yinpeng Dong , Wenzhao Xiang , Xiao Yang , Hang Su , Jun Zhu , Yuefeng Chen , Yuan He , Hui Xue , Shibao Zheng

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique has been proposed…

Machine Learning · Computer Science 2019-06-18 Jeremy M Cohen , Elan Rosenfeld , J. Zico Kolter

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of…

Adverse-weather image restoration (e.g., rain, snow, haze) models remain highly vulnerable to gradient-based white-box adversarial attacks, wherein minimal loss-aligned perturbations cause substantial degradation in the restored output.…

Machine Learning · Computer Science 2026-01-09 Vladimir Frants , Sos Agaian

Privacy and confidentiality of medical data are of utmost importance in healthcare settings. ViTs, the SOTA vision model, rely on large amounts of patient data for training, which raises concerns about data security and the potential for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Raza Imam , Muhammad Huzaifa , Mohammed El-Amine Azz

Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity due to their speed, ease of deployment, and ability to work…

Image and Video Processing · Electrical Eng. & Systems 2021-12-30 Kartikeya Bhardwaj , Dibakar Gope , James Ward , Paul Whatmough , Danny Loh

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Shaohui Mei , Jiawei Lian , Xiaofei Wang , Yuru Su , Mingyang Ma , Lap-Pui Chau

Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset. While the methods excel in recovering highly contaminated images, we observe that…

Image and Video Processing · Electrical Eng. & Systems 2022-04-07 Chaewon Kim , Jaeho Lee , Jinwoo Shin

We propose a novel and effective purification based adversarial defense method against pre-processor blind white- and black-box attacks. Our method is computationally efficient and trained only with self-supervised learning on general…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Sungmin Cha , Naeun Ko , Youngjoon Yoo , Taesup Moon
‹ Prev 1 4 5 6 7 8 10 Next ›