Gradient-based Data Subversion Attack Against Binary Classifiers
Authors: Rosni K Vasu, Sanjay Seetharaman, Shubham Malaviya, Manish Shukla, Sachin Lodha | Published: 2021-05-31
Poisoning
Evaluating Resilience of Encrypted Traffic Classification Against Adversarial Evasion Attacks
Authors: Ramy Maarouf, Danish Sattar, Ashraf Matrawy | Published: 2021-05-30
Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness
Authors: Glenn Dawson, Robi Polikar | Published: 2021-05-28 | Updated: 2021-06-05
Fooling Partial Dependence via Data Poisoning
Authors: Hubert Baniecki, Wojciech Kretowicz, Przemyslaw Biecek | Published: 2021-05-26 | Updated: 2022-07-10
Regularization Can Help Mitigate Poisoning Attacks… with the Right Hyperparameters
Authors: Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu | Published: 2021-05-23
Preventing Machine Learning Poisoning Attacks Using Authentication and Provenance
Authors: Jack W. Stokes, Paul England, Kevin Kane | Published: 2021-05-20
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
Authors: Xiaoyu Zhang, Chao Chen, Yi Xie, Xiaofeng Chen, Jun Zhang, Yang Xiang | Published: 2021-05-13
Mental Models of Adversarial Machine Learning
Authors: Lukas Bieringer, Kathrin Grosse, Michael Backes, Battista Biggio, Katharina Krombholz | Published: 2021-05-08 | Updated: 2022-06-29
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
Authors: Charles Jin, Melinda Sun, Martin Rinard | Published: 2021-05-08 | Updated: 2023-04-27
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks
Authors: Jian Chen, Xuxin Zhang, Rui Zhang, Chen Wang, Ling Liu | Published: 2021-05-08