Yu, Y.J.[Young-Joon],
Lee, H.J.[Hong Joo],
Lee, H.[Hakmin],
Ro, Y.M.[Yong Man],
Defending Person Detection Against Adversarial Patch Attack by Using
Universal Defensive Frame,
IP(31), 2022, pp. 6976-6990.
IEEE DOI
2212
Detectors, Task analysis, Optimization, Robustness, Training, Security,
Head, Adversarial patch, defensive pattern,
person detection
BibRef
Zhang, Y.C.[Yi-Chuang],
Zhang, Y.[Yu],
Qi, J.H.[Jia-Hao],
Bin, K.C.[Kang-Cheng],
Wen, H.[Hao],
Tong, X.Q.[Xun-Qian],
Zhong, P.[Ping],
Adversarial Patch Attack on Multi-Scale Object Detection for UAV
Remote Sensing Images,
RS(14), No. 21, 2022, pp. xx-yy.
DOI Link
2212
BibRef
Shi, M.C.[Meng-Chen],
Xie, F.[Fei],
Yang, J.Q.[Ji-Quan],
Zhao, J.[Jing],
Liu, X.X.[Xi-Xiang],
Wang, F.[Fan],
Cutout with patch-loss augmentation for improving generative
adversarial networks against instability,
CVIU(234), 2023, pp. 103761.
Elsevier DOI
2307
Generative Adversarial Networks, Dataset augmentation,
Convolution neural network
BibRef
Pintor, M.[Maura],
Angioni, D.[Daniele],
Sotgiu, A.[Angelo],
Demetrio, L.[Luca],
Demontis, A.[Ambra],
Biggio, B.[Battista],
Roli, F.[Fabio],
ImageNet-Patch: A dataset for benchmarking machine learning
robustness against adversarial patches,
PR(134), 2023, pp. 109064.
Elsevier DOI
2212
Adversarial machine learning, Adversarial patches,
Neural networks, Defense, Detection
BibRef
Wang, Z.[Zhen],
Wang, B.H.[Bu-Hong],
Zhang, C.L.[Chuan-Lei],
Liu, Y.H.[Yao-Hui],
Defense against Adversarial Patch Attacks for Aerial Image Semantic
Segmentation by Robust Feature Extraction,
RS(15), No. 6, 2023, pp. 1690.
DOI Link
2304
BibRef
Wang, Z.[Zhen],
Wang, B.H.[Bu-Hong],
Zhang, C.L.[Chuan-Lei],
Liu, Y.H.[Yao-Hui],
Guo, J.X.[Jian-Xin],
Robust Feature-Guided Generative Adversarial Network for Aerial Image
Semantic Segmentation against Backdoor Attacks,
RS(15), No. 10, 2023, pp. xx-yy.
DOI Link
2306
BibRef
Wang, Z.[Zhen],
Wang, B.H.[Bu-Hong],
Zhang, C.L.[Chuan-Lei],
Liu, Y.H.[Yao-Hui],
Guo, J.X.[Jian-Xin],
Defending against Poisoning Attacks in Aerial Image Semantic
Segmentation with Robust Invariant Feature Enhancement,
RS(15), No. 12, 2023, pp. xx-yy.
DOI Link
2307
BibRef
Wei, X.X.[Xing-Xing],
Guo, Y.[Ying],
Yu, J.[Jie],
Zhang, B.[Bo],
Simultaneously Optimizing Perturbations and Positions for Black-Box
Adversarial Patch Attacks,
PAMI(45), No. 7, July 2023, pp. 9041-9054.
IEEE DOI
2306
Perturbation methods, Face recognition, Task analysis,
Optimization, Closed box, Estimation, Detectors, Adversarial patches,
traffic sign recognition
BibRef
Ran, Y.[Yu],
Wang, W.J.[Wei-Jia],
Li, M.J.[Ming-Jie],
Li, L.C.[Lin-Cheng],
Wang, Y.G.[Yuan-Gen],
Li, J.[Jin],
Cross-Shaped Adversarial Patch Attack,
CirSysVideo(34), No. 4, April 2024, pp. 2289-2303.
IEEE DOI
2404
Closed box, Perturbation methods, Glass box, Shape,
Image segmentation, Computational modeling, Predictive models,
cross-shaped patch
BibRef
Yang, J.[Jian],
Guan, Z.Y.[Zhi-Yu],
Li, J.[Jun],
Shi, Z.P.[Zhi-Ping],
Liu, X.L.[Xiang-Long],
Diffusion Patch Attack With Spatial-Temporal Cross-Evolution for
Video Recognition,
CirSysVideo(34), No. 12, December 2024, pp. 13190-13200.
IEEE DOI
2501
Closed box, Diffusion models, Classification algorithms,
Perturbation methods, Optimization,
video action recognition
BibRef
Qi, L.[Lei],
Zhao, D.J.[Dong-Jia],
Shi, Y.H.[Ying-Huan],
Geng, X.[Xin],
Patch-Aware Batch Normalization for Improving Cross-Domain Robustness,
CirSysVideo(35), No. 1, January 2025, pp. 800-810.
IEEE DOI
2502
Training, Batch normalization, Robustness, Object detection,
Adversarial machine learning, Semantics, Standards, MixPatch
BibRef
Wei, X.X.[Xing-Xing],
Ruan, S.[Shouwei],
Dong, Y.P.[Yin-Peng],
Su, H.[Hang],
Cao, X.C.[Xiao-Chun],
Distributionally Location-Aware Transferable Adversarial Patches for
Facial Images,
PAMI(47), No. 4, April 2025, pp. 2849-2864.
IEEE DOI
2503
Face recognition, Optimization, Closed box, Robustness,
Visualization, Perturbation methods, Computational modeling,
transfer-based attack
BibRef
Yang, J.[Jian],
Li, J.[Jun],
Cai, Y.[Yunong],
Wu, G.M.[Guo-Ming],
Shi, Z.P.[Zhi-Ping],
Tan, C.[Chaodong],
Liu, X.L.[Xiang-Long],
Hard-Sample Style Guided Patch Attack With RL-Enhanced Motion Pattern
for Video Recognition,
MultMed(27), 2025, pp. 1205-1215.
IEEE DOI
2503
Closed box, Perturbation methods, Search problems,
Image recognition, Generators, Target recognition, Noise, Glass box,
video action recognition
BibRef
Kang, C.X.[Cai-Xin],
Dong, Y.P.[Yin-Peng],
Wang, Z.Y.[Zheng-Yi],
Ruan, S.[Shouwei],
Chen, Y.[Yubo],
Su, H.[Hang],
Wei, X.X.[Xing-Xing],
Diffender: Diffusion-based Adversarial Defense Against Patch Attacks,
ECCV24(LII: 130-147).
Springer DOI
2412
BibRef
Yang, M.Y.[Ming-Yu],
Liu, D.[Daizong],
Tang, K.[Keke],
Zhou, P.[Pan],
Chen, L.X.[Li-Xing],
Chen, J.Y.[Jun-Yang],
Hiding Imperceptible Noise in Curvature-aware Patches for 3d Point
Cloud Attack,
ECCV24(XXX: 431-448).
Springer DOI
2412
BibRef
Wu, S.Y.[Si-Yang],
Wang, J.[Jiakai],
Zhao, J.[Jiejie],
Wang, Y.[Yazhe],
Liu, X.L.[Xiang-Long],
NAPGuard: Towards Detecting Naturalistic Adversarial Patches,
CVPR24(24367-24376)
IEEE DOI Code:
WWW Link.
2410
Training, Accuracy, Codes, Modulation, Benchmark testing,
Feature extraction, adversarial patch, adversarial defense,
object detection
BibRef
Jing, L.H.[Li-Hua],
Wang, R.[Rui],
Ren, W.Q.[Wen-Qi],
Dong, X.[Xin],
Zou, C.[Cong],
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks,
CVPR24(24472-24481)
IEEE DOI Code:
WWW Link.
2410
Training, Location awareness, Image quality, Shape, Semantics, Noise
BibRef
Gittings, T.[Thomas],
Schneider, S.[Steve],
Collomosse, J.[John],
SegGuard: Defending Scene Segmentation Against Adversarial Patch
Attack,
ICIP24(794-800)
IEEE DOI
2411
Training, Semantic segmentation, Semantics, Production,
Network architecture, Generative adversarial networks,
Adversarial Attack
BibRef
Zhao, Q.[Qun],
Wang, Y.G.[Yuan-Gen],
Universal Black-Box Adversarial Patch Attack with Optimized Genetic
Algorithm,
ICIP24(780-786)
IEEE DOI
2411
Diversity reception, Closed box, Estimation, Space exploration,
Optimization, Genetic algorithms, Adversarial example,
hard-label black-box attackgenetic algorithm
BibRef
Chattopadhyay, N.[Nandish],
Guesmi, A.[Amira],
Shafique, M.[Muhammad],
Anomaly Unveiled: Securing Image Classification against Adversarial
Patch Attacks,
ICIP24(929-935)
IEEE DOI
2411
Deep learning, Image segmentation, Accuracy, Pipelines, Noise,
Neural networks, Task analysis, Adversarial patch, clustering
BibRef
Jiang, K.X.[Kai-Xun],
Chen, Z.Y.[Zhao-Yu],
Huang, H.[Hao],
Wang, J.F.[Jia-Feng],
Yang, D.K.[Ding-Kang],
Li, B.[Bo],
Wang, Y.[Yan],
Zhang, W.Q.[Wen-Qiang],
Efficient Decision-based Black-box Patch Attacks on Video Recognition,
ICCV23(4356-4366)
IEEE DOI
2401
BibRef
Hingun, N.[Nabeel],
Sitawarin, C.[Chawin],
Li, J.[Jerry],
Wagner, D.[David],
REAP: A Large-Scale Realistic Adversarial Patch Benchmark,
ICCV23(4617-4628)
IEEE DOI Code:
WWW Link.
2401
BibRef
Tarchoun, B.[Bilel],
Ben Khalifa, A.[Anouar],
Mahjoub, M.A.[Mohamed Ali],
Abu-Ghazaleh, N.[Nael],
Alouani, I.[Ihsen],
Jedi: Entropy-Based Localization and Removal of Adversarial Patches,
CVPR23(4087-4095)
IEEE DOI
2309
BibRef
Xu, K.[Ke],
Xiao, Y.[Yao],
Zheng, Z.H.[Zhao-Heng],
Cai, K.[Kaijie],
Nevatia, R.[Ram],
PatchZero: Defending against Adversarial Patch Attacks by Detecting
and Zeroing the Patch,
WACV23(4621-4630)
IEEE DOI
2302
Training, Degradation, Shape, Pipelines, Neural networks, Object detection,
Robustness, Algorithms: Adversarial learning, visual reasoning
BibRef
Li, J.[Junbo],
Zhang, H.[Huan],
Xie, C.[Cihang],
ViP: Unified Certified Detection and Recovery for Patch Attack with
Vision Transformers,
ECCV22(XXV:573-587).
Springer DOI
2211
BibRef
Lovisotto, G.[Giulio],
Finnie, N.[Nicole],
Munoz, M.[Mauricio],
Murnmadi, C.K.[Chaithanya Kumar],
Metzen, J.H.[Jan Hendrik],
Give Me Your Attention: Dot-Product Attention Considered Harmful for
Adversarial Patch Robustness,
CVPR22(15213-15222)
IEEE DOI
2210
Image recognition, Object detection, Transformer cores,
Transformers, Robustness, Cognition, Machine learning
BibRef
Liu, J.[Jiang],
Levine, A.[Alexander],
Lau, C.P.[Chun Pong],
Chellappa, R.[Rama],
Feizi, S.[Soheil],
Segment and Complete: Defending Object Detectors against Adversarial
Patch Attacks with Robust Patch Detection,
CVPR22(14953-14962)
IEEE DOI
2210
Training, Location awareness, Image segmentation, Shape, Detectors,
Object detection, Adversarial attack and defense
BibRef
Yu, C.[Cheng],
Chen, J.S.[Jian-Sheng],
Xue, Y.[Youze],
Liu, Y.Y.[Yu-Yang],
Wan, W.T.[Wei-Tao],
Bao, J.Y.[Jia-Yu],
Ma, H.M.[Hui-Min],
Defending against Universal Adversarial Patches by Clipping Feature
Norms,
ICCV21(16414-16422)
IEEE DOI
2203
Training, Visualization, Computational modeling,
Robustness, Convolutional neural networks,
Recognition and classification
BibRef
Nesti, F.[Federico],
Rossolini, G.[Giulio],
Nair, S.[Saasha],
Biondi, A.[Alessandro],
Buttazzo, G.[Giorgio],
Evaluating the Robustness of Semantic Segmentation for Autonomous
Driving against Real-World Adversarial Patch Attacks,
WACV22(2826-2835)
IEEE DOI
2202
Computational modeling, Perturbation methods, Semantics, Pipelines,
Grouping and Shape
BibRef
Lennon, M.[Max],
Drenkow, N.[Nathan],
Burlina, P.[Phil],
Patch Attack Invariance: How Sensitive are Patch Attacks to 3D Pose?,
AROW21(112-121)
IEEE DOI
2112
Measurement, Training, Heating systems,
Sensitivity analysis, Conferences
BibRef
Gittings, T.,
Schneider, S.,
Collomosse, J.,
Vax-a-net: Training-time Defence Against Adversarial Patch Attacks,
ACCV20(IV:235-251).
Springer DOI
2103
BibRef
Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Adversarial Trainning for Defense .