Adversarial perturbations of physical signals
Sign Up to like & getrecommendations! Published in 2024 at "Computational Optimization and Applications"
DOI: 10.1007/s10589-024-00636-x
Abstract: We investigate the vulnerability of computer-vision-based signal classifiers to adversarial perturbations of their inputs, where the signals and perturbations are subject to physical constraints. We consider a scenario in which a source and interferer emit… read more here.
Keywords: adversarial perturbations; physical signals; source; perturbations physical ... See more keywords
Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers
Sign Up to like & getrecommendations! Published in 2021 at "National Science Review"
DOI: 10.1093/nsr/nwaa233
Abstract: Abstract An electroencephalogram (EEG)-based brain–computer interface (BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no… read more here.
Keywords: computer interface; eeg based; adversarial perturbations; computer ... See more keywords
Robust Representation Learning Based on Deep Mutual Information for Scene Classification Against Adversarial Perturbations
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"
DOI: 10.1109/jstars.2025.3564376
Abstract: Remote sensing scene classification enables data-driven decisions for various applications, such as environmental monitoring, urban planning, and disaster management. However, deep learning models used for scene classification are highly vulnerable to adversarial samples, resulting in… read more here.
Keywords: adversarial perturbations; information; scene classification; mutual information ... See more keywords
Perturbation Inactivation Based Adversarial Defense for Face Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2022.3195384
Abstract: Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations. However, the generalization capacities of these methods… read more here.
Keywords: recognition; face recognition; defense; adversarial defense ... See more keywords
No-Box Universal Adversarial Perturbations Against Image Classifiers via Artificial Textures
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2024.3478828
Abstract: Recent advancements in adversarial attack research have seen a transition from white-box to black-box and even no-box threat models, greatly enhancing the practicality of these attacks. However, existing no-box attacks focus on instance-specific perturbations, leaving… read more here.
Keywords: adversarial perturbations; texture; threat; texture adv ... See more keywords
Crafting Adversarial Perturbations via Transformed Image Component Swapping
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2022.3204206
Abstract: Adversarial attacks have been demonstrated to fool the deep classification networks. There are two key characteristics of these attacks: firstly, these perturbations are mostly additive noises carefully crafted from the deep neural network itself. Secondly,… read more here.
Keywords: proposed attack; image components; attack; adversarial perturbations ... See more keywords
Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation.
Sign Up to like & getrecommendations! Published in 2024 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2025.3630185
Abstract: This work studies sparse adversarial perturbations, including both unstructured and structured ones. We propose a framework based on a white-box PGD-like attack method named Sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine… read more here.
Keywords: adversarial perturbations; sparse pgd; pgd; sparse adversarial ... See more keywords
RGN-Defense: erasing adversarial perturbations using deep residual generative network
Sign Up to like & getrecommendations! Published in 2019 at "Journal of Electronic Imaging"
DOI: 10.1117/1.jei.28.1.013027
Abstract: Abstract. In recent years, deep neural networks have achieved great success in various fields, especially in computer vision. However, recent investigations have shown that current state-of-the-art classification models are highly vulnerable to adversarial perturbations contained… read more here.
Keywords: rgn defense; deep residual; adversarial perturbations; defense ... See more keywords
Bridging the gap between individual and universal adversarial perturbations
Sign Up to like & getrecommendations! Published in 2025 at "China Communications"
DOI: 10.23919/jcc.fa.2024-0040.202509
Abstract: In recent years, universal adversarial perturbation (UAP) has attracted the attention of many researchers due to its good generalization. However, in order to generate an appropriate UAP, current methods usually require either accessing the original… read more here.
Keywords: adversarial perturbations; uap; gap individual; universal adversarial ... See more keywords