14.5.10.10.5 Adversarial Trainning for Defense

Seo, S.[Seungwan], Lee, Y.[Yunseung], Kang, P.[Pilsung],
Cost-free adversarial defense: Distance-based optimization for model robustness without adversarial training,
CVIU(227), 2023, pp. 103599.
Elsevier DOI 2301
Adversarial defense, White-box attack, Adversarial robustness, Distance-based defense BibRef

Cheng, Z.[Zhen], Zhu, F.[Fei], Zhang, X.Y.[Xu-Yao], Liu, C.L.[Cheng-Lin],
Adversarial training with distribution normalization and margin balance,
PR(136), 2023, pp. 109182.
Elsevier DOI 2301
Adversarial robustness, Adversarial training, Distribution normalization, Margin balance BibRef

Lau, C.P.[Chun Pong], Liu, J.[Jiang], Souri, H.[Hossein], Lin, W.A.[Wei-An], Feizi, S.[Soheil], Chellappa, R.[Rama],
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses,
PAMI(45), No. 11, November 2023, pp. 13054-13067.
IEEE DOI 2310
BibRef

Miao, J.Z.[Jun-Zhong], Yu, X.Z.[Xiang-Zhan], Hu, Z.C.[Zhi-Chao], Song, Y.[Yanru], Liu, L.[Likun], Zhou, Z.G.[Zhi-Gang],
An effective deep learning adversarial defense method based on spatial structural constraints in embedding space,
PRL(178), 2024, pp. 160-166.
Elsevier DOI 2402
Adversarial defense, Spatial structure, Adversarial training, Generalization, Deep learning BibRef

Song, K.Y.[Kai-Yu], Lai, H.J.[Han-Jiang], Pan, Y.[Yan], Yin, J.[Jian],
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model,
CVPR24(24665-24674)
IEEE DOI Code:
WWW Link. 2410
Costs, Codes, Accuracy, Purification, Perturbation methods, Artificial neural networks, Diffusion Model, Adversarial Perturbation BibRef

Wang, Z.[Zeyu], Li, X.H.[Xian-Hang], Zhu, H.[Hongru], Xie, C.[Cihang],
Revisiting Adversarial Training at Scale,
CVPR24(24675-24685)
IEEE DOI Code:
WWW Link. 2410
Training, Visualization, Accuracy, Costs, Computational modeling, Pipelines, Machine learning BibRef

Xiao, Y.[Yuan], Ma, S.Q.[Shi-Qing], Zhai, J.[Juan], Fang, C.R.[Chun-Rong], Jia, J.Y.[Jin-Yuan], Chen, Z.Y.[Zhen-Yu],
Towards General Robustness Verification of MaxPool-Based Convolutional Neural Networks via Tightening Linear Approximation,
CVPR24(24766-24775)
IEEE DOI Code:
WWW Link. 2410
Perturbation methods, Scalability, Neural networks, Linear approximation, Benchmark testing, Robustness BibRef

Li, Q.[Qian], Hu, Y.X.[Yu-Xiao], Dong, Y.P.[Yin-Peng], Zhang, D.X.[Dong-Xiao], Chen, Y.[Yuntian],
Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training,
CVPR24(24442-24451)
IEEE DOI 2410
Training, Adaptation models, Accuracy, Prevention and mitigation, Robustness BibRef

Yin, X.Y.[Xiang-Yu], Ruan, W.J.[Wen-Jie],
Boosting Adversarial Training via Fisher-Rao Norm-Based Regularization,
CVPR24(24544-24553)
IEEE DOI Code:
WWW Link. 2410
Training, Accuracy, Sensitivity, Computational modeling, Artificial neural networks, Network architecture, Robustness, model complexity BibRef

Tang, L.[Linyu], Zhang, L.[Lei],
Robust Overfitting Does Matter: Test-Time Adversarial Purification with FGSM,
CVPR24(24347-24356)
IEEE DOI Code:
WWW Link. 2410
Training, Accuracy, Codes, Purification, Perturbation methods, Robustness, Adversarial Defense BibRef

Zhao, M.[Mengnan], Zhang, L.[Lihe], Kong, Y.Q.[Yu-Qiu], Yin, B.C.[Bao-Cai],
Fast Adversarial Training with Smooth Convergence,
ICCV23(4697-4706)
IEEE DOI Code:
WWW Link. 2401
BibRef

Ge, Y.[Yao], Li, Y.[Yun], Han, K.[Keji], Zhu, J.[Junyi], Long, X.Z.[Xian-Zhong],
Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training,
ICCV23(145-154)
IEEE DOI Code:
WWW Link. 2401
BibRef

Wei, Z.[Zeming], Wang, Y.F.[Yi-Fei], Guo, Y.W.[Yi-Wen], Wang, Y.[Yisen],
CFA: Class-Wise Calibrated Fair Adversarial Training,
CVPR23(8193-8201)
IEEE DOI 2309
BibRef

Dong, J.H.[Jun-Hao], Moosavi-Dezfooli, S.M.[Seyed-Mohsen], Lai, J.H.[Jian-Huang], Xie, X.H.[Xiao-Hua],
The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training,
CVPR23(24678-24687)
IEEE DOI 2309
BibRef

Hsiung, L.[Lei], Tsai, Y.Y.[Yun-Yun], Chen, P.Y.[Pin-Yu], Ho, T.Y.[Tsung-Yi],
Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations,
CVPR23(24658-24667)
IEEE DOI 2309
BibRef

Jin, G.J.[Gao-Jie], Yi, X.P.[Xin-Ping], Wu, D.Y.[Deng-Yu], Mu, R.H.[Rong-Hui], Huang, X.W.[Xiao-Wei],
Randomized Adversarial Training via Taylor Expansion,
CVPR23(16447-16457)
IEEE DOI 2309
BibRef

Gavrikov, P.[Paul], Keuper, J.[Janis], Keuper, M.[Margret],
An Extended Study of Human-like Behavior under Adversarial Training,
AML23(2361-2368)
IEEE DOI 2309
BibRef

Byun, J.[Junyoung], Go, H.[Hyojun], Cho, S.[Seungju], Kim, C.[Changick],
Exploiting Doubly Adversarial Examples for Improving Adversarial Robustness,
ICIP22(1331-1335)
IEEE DOI 2211
Training, Deep learning, Neural networks, Training data, Robustness, Adversarial training, Robustness BibRef

Wang, Z.[Zi], Li, C.C.[Cheng-Cheng], Li, H.[Husheng],
Adversarial Training of Anti-Distilled Neural Network with Semantic Regulation of Class Confidence,
ICIP22(3576-3580)
IEEE DOI 2211
Training, Knowledge engineering, Image coding, Semantics, Neural networks, Intellectual property, Regulation, Semantic similarity BibRef

Yin, X.[Xuwang], Li, S.Y.[Shi-Ying], Rohde, G.K.[Gustavo K.],
Learning Energy-Based Models with Adversarial Training,
ECCV22(V:209-226).
Springer DOI 2211
BibRef

Yang, S.[Shuo], Xu, C.[Chang],
One Size Does NOT Fit All: Data-Adaptive Adversarial Training,
ECCV22(V:70-85).
Springer DOI 2211
BibRef

Dolatabadi, H.M.[Hadi M.], Erfani, S.[Sarah], Leckie, C.[Christopher],
l8-Robustness and Beyond: Unleashing Efficient Adversarial Training,
ECCV22(XI:467-483).
Springer DOI 2211
BibRef

Jia, X.J.[Xiao-Jun], Zhang, Y.[Yong], Wu, B.Y.[Bao-Yuan], Ma, K.[Ke], Wang, J.[Jue], Cao, X.C.[Xiao-Chun],
LAS-AT: Adversarial Training with Learnable Attack Strategy,
CVPR22(13388-13398)
IEEE DOI 2210
Training, Codes, Databases, Benchmark testing, Robustness, Adversarial attack and defense BibRef

Li, T.[Tao], Wu, Y.[Yingwen], Chen, S.[Sizhe], Fang, K.[Kun], Huang, X.L.[Xiao-Lin],
Subspace Adversarial Training,
CVPR22(13399-13408)
IEEE DOI 2210
Training, Codes, Solids, Robustness, Standards, Adversarial attack and defense, Machine learning, Optimization methods BibRef

Poursaeed, O.[Omid], Jiang, T.X.[Tian-Xing], Yang, H.[Harry], Belongie, S.[Serge], Lim, S.N.[Ser-Nam],
Robustness and Generalization via Generative Adversarial Training,
ICCV21(15691-15700)
IEEE DOI 2203
Training, Deep learning, Image segmentation, Computational modeling, Neural networks, Object detection, Neural generative models BibRef

Xu, W.P.[Wei-Peng], Huang, H.C.[Hong-Cheng], Pan, S.Y.[Shao-You],
Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness In Object Detection,
ICIP21(2184-2188)
IEEE DOI 2201
Training, Object detection, Detectors, Feature extraction, Robustness, deep learning, object detection, adversarial training BibRef

Yu, C.[Cheng], Xue, Y.Z.[You-Ze], Chen, J.S.[Jian-Sheng], Wang, Y.[Yu], Ma, H.M.[Hui-Min],
Enhancing Adversarial Robustness for Image Classification By Regularizing Class Level Feature Distribution,
ICIP21(494-498)
IEEE DOI 2201
Training, Deep learning, Adaptation models, Image processing, Neural networks, Robustness, Adversarial Training, Robustness BibRef

Dabouei, A.[Ali], Taherkhani, F.[Fariborz], Soleymani, S.[Sobhan], Nasrabadi, N.M.[Nasser M.],
Revisiting Outer Optimization in Adversarial Training,
ECCV22(V:244-261).
Springer DOI 2211
BibRef

Dabouei, A.[Ali], Soleymani, S.[Sobhan], Taherkhani, F.[Fariborz], Dawson, J., Nasrabadi, N.M.[Nasser M.],
Exploiting Joint Robustness to Adversarial Perturbations,
CVPR20(1119-1128)
IEEE DOI 2008
Robustness, Perturbation methods, Training, Predictive models, Optimization, Adaptation models BibRef

Addepalli, S.[Sravanti], Jain, S.[Samyak], Sriramanan, G.[Gaurang], Babu, R.V.[R. Venkatesh],
Scaling Adversarial Training to Large Perturbation Bounds,
ECCV22(V:301-316).
Springer DOI 2211
BibRef

Vivek, B.S., Revanur, A.[Ambareesh], Venkat, N.[Naveen], Babu, R.V.[R. Venkatesh],
Plug-And-Pipeline: Efficient Regularization for Single-Step Adversarial Training,
TCV20(138-146)
IEEE DOI 2008
Training, Robustness, Computational modeling, Perturbation methods, Iterative methods, Backpropagation, Data models BibRef

Wang, J., Zhang, H.,
Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks,
ICCV19(6628-6637)
IEEE DOI 2004
entropy, learning (artificial intelligence), neural nets, security of data, adversarial attacks, Data models BibRef

Ye, S., Xu, K., Liu, S., Cheng, H., Lambrechts, J., Zhang, H., Zhou, A., Ma, K., Wang, Y., Lin, X.,
Adversarial Robustness vs. Model Compression, or Both?,
ICCV19(111-120)
IEEE DOI 2004
minimax techniques, neural nets, security of data, adversarial attacks, concurrent adversarial training BibRef

Moosavi-Dezfooli, S.M.[Seyed-Mohsen], Fawzi, A.[Alhussein], Uesato, J.[Jonathan], Frossard, P.[Pascal],
Robustness via Curvature Regularization, and Vice Versa,
CVPR19(9070-9078).
IEEE DOI 2002
Adversarial training leads to more linear boundaries. BibRef

Mummadi, C.K., Brox, T., Metzen, J.H.,
Defending Against Universal Perturbations With Shared Adversarial Training,
ICCV19(4927-4936)
IEEE DOI 2004
image classification, image segmentation, neural nets, universal perturbations, shared adversarial training, Computational modeling BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Noise in Adversarial Attacks, Removing, Detection, Use .