Goldblum, M.[Micah],
Tsipras, D.[Dimitris],
Xie, C.[Chulin],
Chen, X.Y.[Xin-Yun],
Schwarzschild, A.[Avi],
Song, D.[Dawn],
Madry, A.[Aleksander],
Li, B.[Bo],
Goldstein, T.[Tom],
Dataset Security for Machine Learning:
Data Poisoning, Backdoor Attacks, and Defenses,
PAMI(45), No. 2, February 2023, pp. 1563-1580.
IEEE DOI
2301
Data models, Training, Training data, Security, Toxicology,
Unsolicited e-mail, Servers, Data poisoning, backdoor attacks, dataset security
BibRef
Pang, L.[Lu],
Sun, T.[Tao],
Ling, H.B.[Hai-Bin],
Chen, C.[Chao],
Backdoor Cleansing with Unlabeled Data,
CVPR23(12218-12227)
IEEE DOI
2309
BibRef
Zhang, Z.[Zaixi],
Liu, Q.[Qi],
Wang, Z.C.[Zhi-Cai],
Lu, Z.[Zepu],
Hu, Q.Y.[Qing-Yong],
Backdoor Defense via Deconfounded Representation Learning,
CVPR23(12228-12238)
IEEE DOI
2309
BibRef
Yu, Y.[Yi],
Wang, Y.F.[Yu-Fei],
Yang, W.H.[Wen-Han],
Lu, S.J.[Shi-Jian],
Tan, Y.P.[Yap-Peng],
Kot, A.C.[Alex C.],
Backdoor Attacks Against Deep Image Compression via Adaptive
Frequency Trigger,
CVPR23(12250-12259)
IEEE DOI
2309
BibRef
Feng, S.W.[Shi-Wei],
Tao, G.H.[Guan-Hong],
Cheng, S.Y.[Si-Yuan],
Shen, G.Y.[Guang-Yu],
Xu, X.Z.[Xiang-Zhe],
Liu, Y.Q.[Ying-Qi],
Zhang, K.[Kaiyuan],
Ma, S.Q.[Shi-Qing],
Zhang, X.Y.[Xiang-Yu],
Detecting Backdoors in Pre-trained Encoders,
CVPR23(16352-16362)
IEEE DOI
2309
BibRef
Liu, X.[Xiaogeng],
Li, M.H.[Ming-Hui],
Wang, H.Y.[Hao-Yu],
Hu, S.[Shengshan],
Ye, D.[Dengpan],
Jin, H.[Hai],
Wu, L.[Libing],
Xiao, C.W.[Chao-Wei],
Detecting Backdoors During the Inference Stage Based on Corruption
Robustness Consistency,
CVPR23(16363-16372)
IEEE DOI
2309
BibRef
Xu, Q.[Qiuling],
Tao, G.N.[Gua-Nhong],
Honorio, J.[Jean],
Liu, Y.Q.[Ying-Qi],
An, S.W.[Sheng-Wei],
Shen, G.Y.[Guang-Yu],
Cheng, S.Y.[Si-Yuan],
Zhang, X.Y.[Xiang-Yu],
MEDIC: Remove Model Backdoors via Importance Driven Cloning,
CVPR23(20485-20494)
IEEE DOI
2309
BibRef
Chen, S.[Simin],
Chen, H.L.[Han-Lin],
Haque, M.[Mirazul],
Liu, C.[Cong],
Yang, W.[Wei],
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency
Backdoor Injection,
CVPR23(24585-24594)
IEEE DOI
2309
BibRef
Bober-Irizar, M.[Mikel],
Shumailov, I.[Ilia],
Zhao, Y.[Yiren],
Mullins, R.[Robert],
Papernot, N.[Nicolas],
Architectural Backdoors in Neural Networks,
CVPR23(24595-24604)
IEEE DOI
2309
BibRef
Yuan, Z.[Zenghui],
Zhou, P.[Pan],
Zou, K.[Kai],
Cheng, Y.[Yu],
You Are Catching My Attention: Are Vision Transformers Bad Learners
under Backdoor Attacks?,
CVPR23(24605-24615)
IEEE DOI
2309
BibRef
Tejankar, A.[Ajinkya],
Sanjabi, M.[Maziar],
Wang, Q.F.[Qi-Fan],
Wang, S.[Sinong],
Firooz, H.[Hamed],
Pirsiavash, H.[Hamed],
Tan, L.[Liang],
Defending Against Patch-based Backdoor Attacks on Self-Supervised
Learning,
CVPR23(12239-12249)
IEEE DOI
2309
BibRef
Saha, A.[Aniruddha],
Tejankar, A.[Ajinkya],
Koohpayegani, S.A.[Soroush Abbasi],
Pirsiavash, H.[Hamed],
Backdoor Attacks on Self-Supervised Learning,
CVPR22(13327-13336)
IEEE DOI
2210
Deep learning, Toxicology, Computational modeling,
Supervised learning, Crops, Self-supervised learning, Inspection,
Self- semi- meta- unsupervised learning
BibRef
Qi, X.Y.[Xiang-Yu],
Xie, T.H.[Ting-Hao],
Pan, R.Z.[Rui-Zhe],
Zhu, J.F.[Ji-Feng],
Yang, Y.[Yong],
Bu, K.[Kai],
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural
Networks,
CVPR22(13337-13347)
IEEE DOI
2210
Deep learning, Training, Computer viruses, Computational modeling,
Neural networks, Production, Adversarial attack and defense,
Computer vision for social good
BibRef
Huang, S.J.[Shan-Jiaoyang],
Peng, W.Q.[Wei-Qi],
Jia, Z.W.[Zhi-Wei],
Tu, Z.W.[Zhuo-Wen],
One-pixel Signature: Characterizing CNN Models for Backdoor Detection,
ECCV20(XXVII:326-341).
Springer DOI
2011
BibRef
Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Black-Box Attacks, Robustness .