14.5.8.8.2 Countering Adversarial Attacks, Defense, Robustness

Chapter Contents (Back)
Adversarial Networks. Generative Networks. GAN. More for the attack iteslf:
See also Adversarial Attacks.
See also Adversarial Networks, Adversarial Inputs, Generative Adversarial.

Miller, D.J., Xiang, Z., Kesidis, G.,
Adversarial Learning Targeting Deep Neural Network Classification: A Comprehensive Review of Defenses Against Attacks,
PIEEE(108), No. 3, March 2020, pp. 402-433.
IEEE DOI 2003
Training data, Neural networks, Reverse engineering, Machine learning, Robustness, Training data, Feature extraction, white box BibRef

Amini, S., Ghaemmaghami, S.,
Towards Improving Robustness of Deep Neural Networks to Adversarial Perturbations,
MultMed(22), No. 7, July 2020, pp. 1889-1903.
IEEE DOI 2007
Robustness, Perturbation methods, Training, Deep learning, Computer architecture, Neural networks, Signal to noise ratio, interpretable BibRef

Li, X.R.[Xu-Rong], Ji, S.L.[Shou-Ling], Ji, J.T.[Jun-Tao], Ren, Z.Y.[Zhen-Yu], Wu, C.M.[Chun-Ming], Li, B.[Bo], Wang, T.[Ting],
Adversarial examples detection through the sensitivity in space mappings,
IET-CV(14), No. 5, August 2020, pp. 201-213.
DOI Link 2007
BibRef

Li, H., Zeng, Y., Li, G., Lin, L., Yu, Y.,
Online Alternate Generator Against Adversarial Attacks,
IP(29), 2020, pp. 9305-9315.
IEEE DOI 2010
Generators, Training, Perturbation methods, Knowledge engineering, Convolutional neural networks, Deep learning, image classification BibRef

Zhang, Y.G.[Yong-Gang], Tian, X.M.[Xin-Mei], Li, Y.[Ya], Wang, X.C.[Xin-Chao], Tao, D.C.[Da-Cheng],
Principal Component Adversarial Example,
IP(29), 2020, pp. 4804-4815.
IEEE DOI 2003
Manifolds, Neural networks, Perturbation methods, Distortion, Task analysis, Robustness, Principal component analysis, manifold learning BibRef

Ma, X.J.[Xing-Jun], Niu, Y.[Yuhao], Gu, L.[Lin], Wang, Y.[Yisen], Zhao, Y.T.[Yi-Tian], Bailey, J.[James], Lu, F.[Feng],
Understanding adversarial attacks on deep learning based medical image analysis systems,
PR(110), 2021, pp. 107332.
Elsevier DOI 2011
Adversarial attack, Adversarial example detection, Medical image analysis, Deep learning BibRef

Zhou, M.[Mo], Niu, Z.X.[Zhen-Xing], Wang, L.[Le], Zhang, Q.L.[Qi-Lin], Hua, G.[Gang],
Adversarial Ranking Attack and Defense,
ECCV20(XIV:781-799).
Springer DOI 2011
BibRef

Agarwal, A.[Akshay], Vatsa, M.[Mayank], Singh, R.[Richa], Ratha, N.[Nalini],
Cognitive data augmentation for adversarial defense via pixel masking,
PRL(146), 2021, pp. 244-251.
Elsevier DOI 2105
Adversarial attacks, Deep learning, Data augmentation BibRef

Li, Z.R.[Zhuo-Rong], Feng, C.[Chao], Wu, M.H.[Ming-Hui], Yu, H.C.[Hong-Chuan], Zheng, J.W.[Jian-Wei], Zhu, F.[Fanwei],
Adversarial robustness via attention transfer,
PRL(146), 2021, pp. 172-178.
Elsevier DOI 2105
Adversarial defense, Robustness, Representation learning, Visual attention, Transfer learning BibRef

Zhang, S.D.[Shu-Dong], Gao, H.[Haichang], Rao, Q.X.[Qing-Xun],
Defense Against Adversarial Attacks by Reconstructing Images,
IP(30), 2021, pp. 6117-6129.
IEEE DOI 2107
Perturbation methods, Image reconstruction, Training, Iterative methods, Computational modeling, Predictive models, perceptual loss BibRef

Li, N.N.[Nan-Nan], Chen, Z.Z.[Zhen-Zhong],
Toward Visual Distortion in Black-Box Attacks,
IP(30), 2021, pp. 6156-6167.
IEEE DOI 2107
Distortion, Visualization, Measurement, Loss measurement, Optimization, Convergence, Training, Black-box attack, classification BibRef

Zhao, Z.Q.[Zhi-Qun], Wang, H.Y.[Heng-You], Sun, H.[Hao], Yuan, J.H.[Jian-He], Huang, Z.C.[Zhong-Chao], He, Z.H.[Zhi-Hai],
Removing Adversarial Noise via Low-Rank Completion of High-Sensitivity Points,
IP(30), 2021, pp. 6485-6497.
IEEE DOI 2107
Perturbation methods, Training, Neural networks, Image denoising, Optimization, TV, Sensitivity, Adversarial examples, TV norm BibRef

Hu, W.Z.[Wen-Zheng], Li, M.Y.[Ming-Yang], Wang, Z.[Zheng], Wang, J.Q.[Jian-Qiang], Zhang, C.S.[Chang-Shui],
DiFNet: Densely High-Frequency Convolutional Neural Networks,
SPLetters(28), 2021, pp. 1340-1344.
IEEE DOI 2107
Image edge detection, Convolution, Perturbation methods, Training, Neural networks, Computer architecture, Robustness, Robust, deep convolution neural network BibRef

Mustafa, A.[Aamir], Khan, S.H.[Salman H.], Hayat, M.[Munawar], Goecke, R.[Roland], Shen, J.B.[Jian-Bing], Shao, L.[Ling],
Deeply Supervised Discriminative Learning for Adversarial Defense,
PAMI(43), No. 9, September 2021, pp. 3154-3166.
IEEE DOI 2108
Robustness, Perturbation methods, Training, Linear programming, Optimization, Marine vehicles, Prototypes, Adversarial defense, deep supervision BibRef

Karim, F.[Fazle], Majumdar, S.[Somshubra], Darabi, H.S.[Hou-Shang],
Adversarial Attacks on Time Series,
PAMI(43), No. 10, October 2021, pp. 3309-3320.
IEEE DOI 2109
Time series analysis, Computational modeling, Data models, Neural networks, Machine learning, Training, deep learning BibRef

Khodabakhsh, A.[Ali], Akhtar, Z.[Zahid],
Unknown presentation attack detection against rational attackers,
IET-Bio(10), No. 5, 2021, pp. 460-479.
DOI Link 2109
BibRef

Zhang, X.W.[Xing-Wei], Zheng, X.[Xiaolong], Mao, W.J.[Wen-Ji],
Adversarial Perturbation Defense on Deep Neural Networks,
Surveys(54), No. 8, October 2021, pp. xx-yy.
DOI Link 2110
Survey, Adversarial Defense. security, deep neural networks, origin, Adversarial perturbation defense BibRef

Chen, X.[Xuan], Ma, Y.[YueNa], Lu, S.[ShiWei], Yao, Y.[Yu],
Boundary augment: A data augment method to defend poison attack,
IET-IPR(15), No. 13, 2021, pp. 3292-3303.
DOI Link 2110
BibRef

Xu, Y.H.[Yong-Hao], Du, B.[Bo], Zhang, L.P.[Liang-Pei],
Self-Attention Context Network: Addressing the Threat of Adversarial Attacks for Hyperspectral Image Classification,
IP(30), 2021, pp. 8671-8685.
IEEE DOI 2110
Deep learning, Training, Hyperspectral imaging, Feature extraction, Task analysis, Perturbation methods, Predictive models, deep learning BibRef

Yu, H.[Hang], Liu, A.S.[Ai-Shan], Li, G.C.[Geng-Chao], Yang, J.C.[Ji-Chen], Zhang, C.Z.[Chong-Zhi],
Progressive Diversified Augmentation for General Robustness of DNNs: A Unified Approach,
IP(30), 2021, pp. 8955-8967.
IEEE DOI 2111
Robustness, Training, Handheld computers, Perturbation methods, Complexity theory, Streaming media, Standards BibRef


Addepalli, S.[Sravanti], Jain, S.[Samyak], Sriramanan, G.[Gaurang], Babu, R.V.[R. Venkatesh],
Boosting Adversarial Robustness using Feature Level Stochastic Smoothing,
SAIAD21(93-102)
IEEE DOI 2109
Training, Deep learning, Smoothing methods, Boosting, Feature extraction BibRef

Pestana, C.[Camilo], Liu, W.[Wei], Glance, D.[David], Mian, A.[Ajmal],
Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty,
WACV21(556-565)
IEEE DOI 2106
Measurement, Deep learning, Machine learning algorithms, Image recognition BibRef

Ali, A.[Arslan], Migliorati, A.[Andrea], Bianchi, T.[Tiziano], Magli, E.[Enrico],
Beyond Cross-Entropy: Learning Highly Separable Feature Distributions for Robust and Accurate Classification,
ICPR21(9711-9718)
IEEE DOI 2105
Robustness to adversarial attacks. Training, Deep learning, Perturbation methods, Gaussian distribution, Linear programming, Robustness BibRef

Kyatham, V.[Vinay], Mishra, D.[Deepak], Prathosh, A.P.,
Variational Inference with Latent Space Quantization for Adversarial Resilience,
ICPR21(9593-9600)
IEEE DOI 2105
Manifolds, Degradation, Quantization (signal), Perturbation methods, Neural networks, Data models, Real-time systems BibRef

Li, H.[Honglin], Fan, Y.[Yifei], Ganz, F.[Frieder], Yezzi, A.J.[Anthony J.], Barnaghi, P.[Payam],
Verifying the Causes of Adversarial Examples,
ICPR21(6750-6757)
IEEE DOI 2105
Geometry, Perturbation methods, Neural networks, Linearity, Estimation, Aerospace electronics, Probabilistic logic BibRef

Hou, Y.[Yufan], Zou, L.X.[Li-Xin], Liu, W.D.[Wei-Dong],
Task-based Focal Loss for Adversarially Robust Meta-Learning,
ICPR21(2824-2829)
IEEE DOI 2105
Training, Perturbation methods, Resists, Machine learning, Benchmark testing, Robustness BibRef

Huang, Y.T.[Yen-Ting], Liao, W.H.[Wen-Hung], Huang, C.W.[Chen-Wei],
Defense Mechanism Against Adversarial Attacks Using Density-based Representation of Images,
ICPR21(3499-3504)
IEEE DOI 2105
Deep learning, Perturbation methods, Transforms, Hybrid power systems, Pattern recognition, Intelligent systems BibRef

Chhabra, S.[Saheb], Agarwal, A.[Akshay], Singh, R.[Richa], Vatsa, M.[Mayank],
Attack Agnostic Adversarial Defense via Visual Imperceptible Bound,
ICPR21(5302-5309)
IEEE DOI 2105
Visualization, Sensitivity, Databases, Computational modeling, Perturbation methods, Predictive models, Prediction algorithms BibRef

Šircelj, J.[Jaka], Skocaj, D.[Danijel],
Accuracy-Perturbation Curves for Evaluation of Adversarial Attack and Defence Methods,
ICPR21(6290-6297)
IEEE DOI 2105
Training, Visualization, Perturbation methods, Machine learning, Robustness, Generators, Pattern recognition BibRef

Watson, M.[Matthew], Moubayed, N.A.[Noura Al],
Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning,
ICPR21(8180-8187)
IEEE DOI 2105
Training, Deep learning, Perturbation methods, MIMICs, Medical services, Predictive models, Feature extraction, Medical Data BibRef

Alamri, F.[Faisal], Kalkan, S.[Sinan], Pugeault, N.[Nicolas],
Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection,
ICPR21(9577-9584)
IEEE DOI 2105
Visualization, Perturbation methods, Detectors, Object detection, Transforms, Field-flow fractionation, Feature extraction BibRef

Bouniot, Q.[Quentin], Audigier, R.[Romaric], Loesch, A.[Angelique],
Optimal Transport as a Defense Against Adversarial Attacks,
ICPR21(5044-5051)
IEEE DOI 2105
Training, Deep learning, Measurement, Adaptation models, Perturbation methods, Image representation, Market research BibRef

Schwartz, D.[Daniel], Alparslan, Y.[Yigit], Kim, E.[Edward],
Regularization and Sparsity for Adversarial Robustness and Stable Attribution,
ISVC20(I:3-14).
Springer DOI 2103
BibRef

Carrara, F.[Fabio], Caldelli, R.[Roberto], Falchi, F.[Fabrizio], Amato, G.[Giuseppe],
Defending Neural ODE Image Classifiers from Adversarial Attacks with Tolerance Randomization,
MMForWild20(425-438).
Springer DOI 2103
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

Yi, C., Li, H., Wan, R., Kot, A.C.,
Improving Robustness of DNNs against Common Corruptions via Gaussian Adversarial Training,
VCIP20(17-20)
IEEE DOI 2102
Robustness, Perturbation methods, Training, Neural networks, Standards, Gaussian noise, Tensors, Deep Learning, Data Augmentation BibRef

Rusak, E.[Evgenia], Schott, L.[Lukas], Zimmermann, R.S.[Roland S.], Bitterwolf, J.[Julian], Bringmann, O.[Oliver], Bethge, M.[Matthias], Brendel, W.[Wieland],
A Simple Way to Make Neural Networks Robust Against Diverse Image Corruptions,
ECCV20(III:53-69).
Springer DOI 2012
BibRef

Li, Y.W.[Ying-Wei], Bai, S.[Song], Xie, C.H.[Ci-Hang], Liao, Z.Y.[Zhen-Yu], Shen, X.H.[Xiao-Hui], Yuille, A.L.[Alan L.],
Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses,
ECCV20(XI:795-813).
Springer DOI 2011
BibRef

Shao, R.[Rui], Perera, P.[Pramuditha], Yuen, P.C.[Pong C.], Patel, V.M.[Vishal M.],
Open-set Adversarial Defense,
ECCV20(XVII:682-698).
Springer DOI 2011
BibRef

Bui, A.[Anh], Le, T.[Trung], Zhao, H.[He], Montague, P.[Paul], deVel, O.[Olivier], Abraham, T.[Tamas], Phung, D.[Dinh],
Improving Adversarial Robustness by Enforcing Local and Global Compactness,
ECCV20(XXVII:209-223).
Springer DOI 2011
BibRef

Xu, J., Li, Y., Jiang, Y., Xia, S.T.,
Adversarial Defense Via Local Flatness Regularization,
ICIP20(2196-2200)
IEEE DOI 2011
Training, Standards, Perturbation methods, Robustness, Visualization, Linearity, Taylor series, adversarial defense, gradient-based regularization BibRef

Maung, M., Pyone, A., Kiya, H.,
Encryption Inspired Adversarial Defense For Visual Classification,
ICIP20(1681-1685)
IEEE DOI 2011
Training, Transforms, Encryption, Perturbation methods, Machine learning, Adversarial defense, perceptual image encryption BibRef

Shah, S.A.A., Bougre, M., Akhtar, N., Bennamoun, M., Zhang, L.,
Efficient Detection of Pixel-Level Adversarial Attacks,
ICIP20(718-722)
IEEE DOI 2011
Robots, Training, Perturbation methods, Machine learning, Robustness, Task analysis, Testing, Adversarial attack, perturbation detection, deep learning BibRef

Jia, S.[Shuai], Ma, C.[Chao], Song, Y.B.[Yi-Bing], Yang, X.K.[Xiao-Kang],
Robust Tracking Against Adversarial Attacks,
ECCV20(XIX:69-84).
Springer DOI 2011
BibRef

Wang, R.[Ren], Zhang, G.Y.[Gao-Yuan], Liu, S.J.[Si-Jia], Chen, P.Y.[Pin-Yu], Xiong, J.J.[Jin-Jun], Wang, M.[Meng],
Practical Detection of Trojan Neural Networks: Data-limited and Data-free Cases,
ECCV20(XXIII:222-238).
Springer DOI 2011
(or poisoning backdoor attack) Manipulate the learned network. BibRef

Mao, C.Z.[Cheng-Zhi], Gupta, A.[Amogh], Nitin, V.[Vikram], Ray, B.[Baishakhi], Song, S.[Shuran], Yang, J.F.[Jun-Feng], Vondrick, C.[Carl],
Multitask Learning Strengthens Adversarial Robustness,
ECCV20(II:158-174).
Springer DOI 2011
BibRef

Li, S.[Shasha], Zhu, S.T.[Shi-Tong], Paul, S.[Sudipta], Roy-Chowdhury, A.[Amit], Song, C.Y.[Cheng-Yu], Krishnamurthy, S.[Srikanth], Swami, A.[Ananthram], Chan, K.S.[Kevin S.],
Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency,
ECCV20(XXIII:396-413).
Springer DOI 2011
BibRef

Li, Y.[Yueru], Cheng, S.Y.[Shu-Yu], Su, H.[Hang], Zhu, J.[Jun],
Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds,
ECCV20(XXVIII:753-769).
Springer DOI 2011
BibRef

Rounds, J.[Jeremiah], Kingsland, A.[Addie], Henry, M.J.[Michael J.], Duskin, K.R.[Kayla R.],
Probing for Artifacts: Detecting Imagenet Model Evasions,
AML-CV20(3432-3441)
IEEE DOI 2008
Perturbation methods, Probes, Computational modeling, Robustness, Image color analysis, Machine learning, Indexes BibRef

Kariyappa, S., Qureshi, M.K.,
Defending Against Model Stealing Attacks With Adaptive Misinformation,
CVPR20(767-775)
IEEE DOI 2008
Data models, Adaptation models, Cloning, Predictive models, Computational modeling, Security, Perturbation methods BibRef

Mohapatra, J., Weng, T., Chen, P., Liu, S., Daniel, L.,
Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations,
CVPR20(241-249)
IEEE DOI 2008
Semantics, Perturbation methods, Robustness, Image color analysis, Brightness, Neural networks, Tools BibRef

Liu, X., Xiao, T., Si, S., Cao, Q., Kumar, S., Hsieh, C.,
How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework,
CVPR20(279-287)
IEEE DOI 2008
Neural networks, Robustness, Stochastic processes, Training, Random variables, Gaussian noise, Mathematical model BibRef

Wu, M., Kwiatkowska, M.,
Robustness Guarantees for Deep Neural Networks on Videos,
CVPR20(308-317)
IEEE DOI 2008
Robustness, Videos, Optical imaging, Adaptive optics, Optical sensors, Measurement, Neural networks BibRef

Chan, A., Tay, Y., Ong, Y.,
What It Thinks Is Important Is Important: Robustness Transfers Through Input Gradients,
CVPR20(329-338)
IEEE DOI 2008
Robustness, Task analysis, Training, Computational modeling, Perturbation methods, Impedance matching, Predictive models BibRef

Zhang, L., Yu, M., Chen, T., Shi, Z., Bao, C., Ma, K.,
Auxiliary Training: Towards Accurate and Robust Models,
CVPR20(369-378)
IEEE DOI 2008
Training, Robustness, Perturbation methods, Neural networks, Data models, Task analysis, Feature extraction BibRef

Baráth, D., Noskova, J., Ivashechkin, M., Matas, J.,
MAGSAC++, a Fast, Reliable and Accurate Robust Estimator,
CVPR20(1301-1309)
IEEE DOI 2008
Robustness, Data models, Estimation, Noise level, Pattern recognition, Kernel BibRef

Saha, A., Subramanya, A., Patil, K., Pirsiavash, H.,
Role of Spatial Context in Adversarial Robustness for Object Detection,
AML-CV20(3403-3412)
IEEE DOI 2008
Detectors, Object detection, Cognition, Training, Blindness, Perturbation methods, Optimization BibRef

Jefferson, B., Marrero, C.O.,
Robust Assessment of Real-World Adversarial Examples,
AML-CV20(3442-3449)
IEEE DOI 2008
Cameras, Light emitting diodes, Robustness, Lighting, Detectors, Testing, Perturbation methods BibRef

Goel, A., Agarwal, A., Vatsa, M., Singh, R., Ratha, N.K.,
DNDNet: Reconfiguring CNN for Adversarial Robustness,
TCV20(103-110)
IEEE DOI 2008
Mathematical model, Perturbation methods, Machine learning, Computer architecture, Robustness, Computational modeling, Databases BibRef

Cohen, G., Sapiro, G., Giryes, R.,
Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors,
CVPR20(14441-14450)
IEEE DOI 2008
Training, Robustness, Loss measurement, Feature extraction, Neural networks, Perturbation methods, Training data BibRef

He, Z., Rakin, A.S., Li, J., Chakrabarti, C., Fan, D.,
Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack,
CVPR20(14083-14091)
IEEE DOI 2008
Training, Neural networks, Random access memory, Indexes, Optimization, Degradation, Immune system BibRef

Dong, X., Han, J., Chen, D., Liu, J., Bian, H., Ma, Z., Li, H., Wang, X., Zhang, W., Yu, N.,
Robust Superpixel-Guided Attentional Adversarial Attack,
CVPR20(12892-12901)
IEEE DOI 2008
Perturbation methods, Robustness, Noise measurement, Image color analysis, Pipelines, Agriculture BibRef

Rahnama, A., Nguyen, A.T., Raff, E.,
Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory,
CVPR20(8175-8184)
IEEE DOI 2008
Robustness, Nonlinear systems, Training, Control theory, Stability analysis, Perturbation methods, Transient analysis BibRef

Zhao, Y., Wu, Y., Chen, C., Lim, A.,
On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks,
CVPR20(1198-1207)
IEEE DOI 2008
Robustness, Data models, Solid modeling, Computational modeling, Perturbation methods BibRef

Gowal, S., Qin, C., Huang, P., Cemgil, T., Dvijotham, K., Mann, T., Kohli, P.,
Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations,
CVPR20(1208-1217)
IEEE DOI 2008
Perturbation methods, Robustness, Training, Semantics, Correlation, Task analysis, Mathematical model BibRef

Jeddi, A., Shafiee, M.J., Karg, M., Scharfenberger, C., Wong, A.,
Learn2Perturb: An End-to-End Feature Perturbation Learning to Improve Adversarial Robustness,
CVPR20(1238-1247)
IEEE DOI 2008
Perturbation methods, Robustness, Training, Neural networks, Data models, Uncertainty, Optimization BibRef

Dabouei, A., Soleymani, S., Taherkhani, F., Dawson, J., Nasrabadi, N.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], Vivek, B.S., Baburaj, A.[Arya], Sriramanan, G.[Gaurang], Babu, R.V.[R. Venkatesh],
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes,
CVPR20(1017-1026)
IEEE DOI 2008
Training, Robustness, Quantization (signal), Visual systems, Perturbation methods, Neural networks BibRef

Yuan, J., He, Z.,
Ensemble Generative Cleaning With Feedback Loops for Defending Adversarial Attacks,
CVPR20(578-587)
IEEE DOI 2008
Cleaning, Feedback loop, Transforms, Neural networks, Estimation, Fuses, Iterative methods BibRef

Guo, M., Yang, Y., Xu, R., Liu, Z., Lin, D.,
When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks,
CVPR20(628-637)
IEEE DOI 2008
Computer architecture, Robustness, Training, Network architecture, Neural networks, Convolution, Architecture BibRef

Borkar, T., Heide, F., Karam, L.,
Defending Against Universal Attacks Through Selective Feature Regeneration,
CVPR20(706-716)
IEEE DOI 2008
Perturbation methods, Training, Robustness, Noise reduction, Image restoration, Transforms BibRef

Li, G., Ding, S., Luo, J., Liu, C.,
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder,
CVPR20(797-805)
IEEE DOI 2008
Noise reduction, Robustness, Training, Image restoration, Noise measurement, Decoding, Neural networks BibRef

Chen, T., Liu, S., Chang, S., Cheng, Y., Amini, L., Wang, Z.,
Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning,
CVPR20(696-705)
IEEE DOI 2008
Robustness, Task analysis, Training, Standards, Data models, Computational modeling, Tuning BibRef

Lee, S., Lee, H., Yoon, S.,
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization,
CVPR20(269-278)
IEEE DOI 2008
Robustness, Training, Standards, Perturbation methods, Complexity theory, Upper bound, Data models BibRef

Dong, Y., Fu, Q., Yang, X., Pang, T., Su, H., Xiao, Z., Zhu, J.,
Benchmarking Adversarial Robustness on Image Classification,
CVPR20(318-328)
IEEE DOI 2008
Robustness, Adaptation models, Training, Predictive models, Perturbation methods, Data models, Measurement BibRef

Xiao, C., Zheng, C.,
One Man's Trash Is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples,
CVPR20(409-418)
IEEE DOI 2008
Training, Robustness, Perturbation methods, Neural networks, Transforms, Mathematical model, Numerical models BibRef

Naseer, M., Khan, S., Hayat, M., Khan, F.S., Porikli, F.M.,
A Self-supervised Approach for Adversarial Robustness,
CVPR20(259-268)
IEEE DOI 2008
Perturbation methods, Task analysis, Distortion, Training, Robustness, Feature extraction, Neural networks BibRef

Zhao, Y., Tian, Y., Fowlkes, C., Shen, W., Yuille, A.L.,
Resisting Large Data Variations via Introspective Transformation Network,
WACV20(3069-3078)
IEEE DOI 2006
Training, Testing, Robustness, Training data, Linear programming, Resists BibRef

Kim, D.H.[Dong-Hyun], Bargal, S.A.[Sarah Adel], Zhang, J.M.[Jian-Ming], Sclaroff, S.[Stan],
Multi-way Encoding for Robustness,
WACV20(1341-1349)
IEEE DOI 2006
To counter adversarial attacks. Encoding, Robustness, Perturbation methods, Training, Biological system modeling, Neurons, Correlation BibRef

Folz, J., Palacio, S., Hees, J., Dengel, A.,
Adversarial Defense based on Structure-to-Signal Autoencoders,
WACV20(3568-3577)
IEEE DOI 2006
Perturbation methods, Semantics, Robustness, Predictive models, Training, Decoding, Neural networks BibRef

Zheng, S., Zhu, Z., Zhang, X., Liu, Z., Cheng, J., Zhao, Y.,
Distribution-Induced Bidirectional Generative Adversarial Network for Graph Representation Learning,
CVPR20(7222-7231)
IEEE DOI 2008
Generative adversarial networks, Robustness, Data models, Generators, Task analysis, Gaussian distribution 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

Benz, P.[Philipp], Zhang, C.[Chaoning], Imtiaz, T.[Tooba], Kweon, I.S.[In So],
Double Targeted Universal Adversarial Perturbations,
ACCV20(IV:284-300).
Springer DOI 2103
BibRef
Earlier: A2,, A1, A3, A4:
Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations,
CVPR20(14509-14518)
IEEE DOI 2008
Perturbation methods, Correlation, Training data, Feature extraction, Training, Task analysis, Robustness BibRef

Zheng, H., Zhang, Z., Gu, J., Lee, H., Prakash, A.,
Efficient Adversarial Training With Transferable Adversarial Examples,
CVPR20(1178-1187)
IEEE DOI 2008
Training, Perturbation methods, Robustness, Computational modeling, Measurement, Iterative methods, Silicon BibRef

Shi, Y., Han, Y., Tian, Q.,
Polishing Decision-Based Adversarial Noise With a Customized Sampling,
CVPR20(1027-1035)
IEEE DOI 2008
Gaussian distribution, Sensitivity, Noise reduction, Optimization, Image coding, Robustness, Standards BibRef

Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A.L., Le, Q.V.,
Adversarial Examples Improve Image Recognition,
CVPR20(816-825)
IEEE DOI 2008
Training, Robustness, Degradation, Image recognition, Perturbation methods, Standards, Supervised learning BibRef

Dabouei, A., Soleymani, S., Taherkhani, F., Dawson, J., Nasrabadi, N.M.,
SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations,
WACV20(2654-2663)
IEEE DOI 2006
Perturbation methods, Frequency-domain analysis, Robustness, Training, Optimization, Network architecture, Topology BibRef

Peterson, J.[Joshua], Battleday, R.[Ruairidh], Griffiths, T.[Thomas], Russakovsky, O.[Olga],
Human Uncertainty Makes Classification More Robust,
ICCV19(9616-9625)
IEEE DOI 2004
CIFAR10H dataset. To make deep network robust ot adversarial attacks. convolutional neural nets, learning (artificial intelligence), pattern classification, classification performance, Dogs 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

Xie, C.[Cihang], Wu, Y.X.[Yu-Xin], van der Maaten, L.[Laurens], Yuille, A.L.[Alan L.], He, K.M.[Kai-Ming],
Feature Denoising for Improving Adversarial Robustness,
CVPR19(501-509).
IEEE DOI 2002
BibRef

He, Z.[Zhezhi], Rakin, A.S.[Adnan Siraj], Fan, D.L.[De-Liang],
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack,
CVPR19(588-597).
IEEE DOI 2002
BibRef

Kaneko, T.[Takuhiro], Harada, T.[Tatsuya],
Noise Robust Generative Adversarial Networks,
CVPR20(8401-8411)
IEEE DOI 2008
Training, Noise measurement, Generators, Noise robustness, Gaussian noise, Image generation BibRef

Kaneko, T.[Takuhiro], Ushiku, Y.[Yoshitaka], Harada, T.[Tatsuya],
Label-Noise Robust Generative Adversarial Networks,
CVPR19(2462-2471).
IEEE DOI 2002
BibRef

Stutz, D.[David], Hein, M.[Matthias], Schiele, B.[Bernt],
Disentangling Adversarial Robustness and Generalization,
CVPR19(6969-6980).
IEEE DOI 2002
BibRef

Miyazato, S., Wang, X., Yamasaki, T., Aizawa, K.,
Reinforcing the Robustness of a Deep Neural Network to Adversarial Examples by Using Color Quantization of Training Image Data,
ICIP19(884-888)
IEEE DOI 1910
convolutional neural network, adversarial example, color quantization BibRef

Ramanathan, T., Manimaran, A., You, S., Kuo, C.J.,
Robustness of Saak Transform Against Adversarial Attacks,
ICIP19(2531-2535)
IEEE DOI 1910
Saak transform, Adversarial attacks, Deep Neural Networks, Image Classification BibRef

Prakash, A., Moran, N., Garber, S., DiLillo, A., Storer, J.,
Deflecting Adversarial Attacks with Pixel Deflection,
CVPR18(8571-8580)
IEEE DOI 1812
Perturbation methods, Transforms, Minimization, Robustness, Noise reduction, Training, Computer vision 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

Chen, H., Liang, J., Chang, S., Pan, J., Chen, Y., Wei, W., Juan, D.,
Improving Adversarial Robustness via Guided Complement Entropy,
ICCV19(4880-4888)
IEEE DOI 2004
entropy, learning (artificial intelligence), neural nets, probability, adversarial defense, adversarial robustness, BibRef

Bai, Y., Feng, Y., Wang, Y., Dai, T., Xia, S., Jiang, Y.,
Hilbert-Based Generative Defense for Adversarial Examples,
ICCV19(4783-4792)
IEEE DOI 2004
feature extraction, Hilbert transforms, neural nets, security of data, scan mode, advanced Hilbert curve scan order BibRef

Jang, Y., Zhao, T., Hong, S., Lee, H.,
Adversarial Defense via Learning to Generate Diverse Attacks,
ICCV19(2740-2749)
IEEE DOI 2004
learning (artificial intelligence), neural nets, pattern classification, security of data, adversarial defense, Machine learning BibRef

Mustafa, A., Khan, S., Hayat, M., Goecke, R., Shen, J., Shao, L.,
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks,
ICCV19(3384-3393)
IEEE DOI 2004
convolutional neural nets, feature extraction, image classification, image representation, Iterative methods BibRef

Taran, O.[Olga], Rezaeifar, S.[Shideh], Holotyak, T.[Taras], Voloshynovskiy, S.[Slava],
Defending Against Adversarial Attacks by Randomized Diversification,
CVPR19(11218-11225).
IEEE DOI 2002
BibRef

Sun, B.[Bo], Tsai, N.H.[Nian-Hsuan], Liu, F.C.[Fang-Chen], Yu, R.[Ronald], Su, H.[Hao],
Adversarial Defense by Stratified Convolutional Sparse Coding,
CVPR19(11439-11448).
IEEE DOI 2002
BibRef

Ho, C.H.[Chih-Hui], Leung, B.[Brandon], Sandstrom, E.[Erik], Chang, Y.[Yen], Vasconcelos, N.M.[Nuno M.],
Catastrophic Child's Play: Easy to Perform, Hard to Defend Adversarial Attacks,
CVPR19(9221-9229).
IEEE DOI 2002
BibRef

Dubey, A.[Abhimanyu], van der Maaten, L.[Laurens], Yalniz, Z.[Zeki], Li, Y.[Yixuan], Mahajan, D.[Dhruv],
Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search,
CVPR19(8759-8768).
IEEE DOI 2002
BibRef

Dong, Y.P.[Yin-Peng], Pang, T.[Tianyu], Su, H.[Hang], Zhu, J.[Jun],
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks,
CVPR19(4307-4316).
IEEE DOI 2002
BibRef

Rony, J.[Jerome], Hafemann, L.G.[Luiz G.], Oliveira, L.S.[Luiz S.], Ben Ayed, I.[Ismail], Sabourin, R.[Robert], Granger, E.[Eric],
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses,
CVPR19(4317-4325).
IEEE DOI 2002
BibRef

Qiu, Y.X.[Yu-Xian], Leng, J.W.[Jing-Wen], Guo, C.[Cong], Chen, Q.[Quan], Li, C.[Chao], Guo, M.[Minyi], Zhu, Y.H.[Yu-Hao],
Adversarial Defense Through Network Profiling Based Path Extraction,
CVPR19(4772-4781).
IEEE DOI 2002
BibRef

Jia, X.J.[Xiao-Jun], Wei, X.X.[Xing-Xing], Cao, X.C.[Xiao-Chun], Foroosh, H.[Hassan],
ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples,
CVPR19(6077-6085).
IEEE DOI 2002
BibRef

Raff, E.[Edward], Sylvester, J.[Jared], Forsyth, S.[Steven], McLean, M.[Mark],
Barrage of Random Transforms for Adversarially Robust Defense,
CVPR19(6521-6530).
IEEE DOI 2002
BibRef

Ji, J., Zhong, B., Ma, K.,
Multi-Scale Defense of Adversarial Images,
ICIP19(4070-4074)
IEEE DOI 1910
deep learning, adversarial images, defense, multi-scale, image evolution BibRef

Agarwal, C., Nguyen, A., Schonfeld, D.,
Improving Robustness to Adversarial Examples by Encouraging Discriminative Features,
ICIP19(3801-3805)
IEEE DOI 1910
Adversarial Machine Learning, Robustness, Defenses, Deep Learning BibRef

Saha, S., Kumar, A., Sahay, P., Jose, G., Kruthiventi, S., Muralidhara, H.,
Attack Agnostic Statistical Method for Adversarial Detection,
SDL-CV19(798-802)
IEEE DOI 2004
feature extraction, image classification, learning (artificial intelligence), neural nets, Adversarial Attack BibRef

Taran, O.[Olga], Rezaeifar, S.[Shideh], Voloshynovskiy, S.[Slava],
Bridging Machine Learning and Cryptography in Defence Against Adversarial Attacks,
Objectionable18(II:267-279).
Springer DOI 1905
BibRef

Naseer, M., Khan, S., Porikli, F.M.,
Local Gradients Smoothing: Defense Against Localized Adversarial Attacks,
WACV19(1300-1307)
IEEE DOI 1904
data compression, feature extraction, gradient methods, image classification, image coding, image representation, High frequency BibRef

Akhtar, N., Liu, J., Mian, A.,
Defense Against Universal Adversarial Perturbations,
CVPR18(3389-3398)
IEEE DOI 1812
Perturbation methods, Training, Computational modeling, Detectors, Neural networks, Robustness, Integrated circuits BibRef

Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J.,
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser,
CVPR18(1778-1787)
IEEE DOI 1812
Training, Perturbation methods, Noise reduction, Image reconstruction, Predictive models, Neural networks, Adaptation models BibRef

Behpour, S., Xing, W., Ziebart, B.D.,
ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-label Classification,
WiCV18(1986-19862)
IEEE DOI 1812
Markov random fields, Task analysis, Training, Testing, Support vector machines, Fasteners, Games BibRef

Karim, R., Islam, M.A., Mohammed, N., Bruce, N.D.B.,
On the Robustness of Deep Learning Models to Universal Adversarial Attack,
CRV18(55-62)
IEEE DOI 1812
Perturbation methods, Computational modeling, Neural networks, Task analysis, Image segmentation, Data models, Semantics, Semantic Segmentation BibRef

Jakubovitz, D.[Daniel], Giryes, R.[Raja],
Improving DNN Robustness to Adversarial Attacks Using Jacobian Regularization,
ECCV18(XII: 525-541).
Springer DOI 1810
BibRef

Rozsa, A., Gunther, M., Boult, T.E.,
Towards Robust Deep Neural Networks with BANG,
WACV18(803-811)
IEEE DOI 1806
image processing, learning (artificial intelligence), neural nets, BANG technique, adversarial image utilization, Training BibRef

Lu, J., Issaranon, T., Forsyth, D.A.,
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly,
ICCV17(446-454)
IEEE DOI 1802
image colour analysis, image reconstruction, learning (artificial intelligence), neural nets, BibRef

Mukuta, Y., Ushiku, Y., Harada, T.,
Spatial-Temporal Weighted Pyramid Using Spatial Orthogonal Pooling,
CEFR-LCV17(1041-1049)
IEEE DOI 1802
Encoding, Feature extraction, Robustness, Spatial resolution, Standards BibRef

Moosavi-Dezfooli, S.M.[Seyed-Mohsen], Fawzi, A.[Alhussein], Fawzi, O.[Omar], Frossard, P.[Pascal],
Universal Adversarial Perturbations,
CVPR17(86-94)
IEEE DOI 1711
Computer architecture, Correlation, Neural networks, Optimization, Robustness, Training, Visualization BibRef

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


Last update:Nov 1, 2021 at 09:26:50