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
Content Specialized for Toxicity Attacks
Being Single Has Benefits. Instance Poisoning to Deceive Malware Classifiers
Authors: Tzvika Shapira, David Berend, Ishai Rosenberg, Yang Liu, Asaf Shabtai, Yuval Elovici | Published: 2020-10-30
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
Authors: Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias | Published: 2020-09-30
A black-box adversarial attack for poisoning clustering
Authors: Antonio Emanuele Cinà, Alessandro Torcinovich, Marcello Pelillo | Published: 2020-09-09 | Updated: 2021-11-10
Defending Regression Learners Against Poisoning Attacks
Authors: Sandamal Weerasinghe, Sarah M. Erfani, Tansu Alpcan, Christopher Leckie, Justin Kopacz | Published: 2020-08-21
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
Authors: Xiang Zhang, Marinka Zitnik | Published: 2020-06-15 | Updated: 2020-10-28
Dynamic Backdoor Attacks Against Machine Learning Models
Authors: Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, Yang Zhang | Published: 2020-03-07 | Updated: 2022-03-03
Can’t Boil This Frog: Robustness of Online-Trained Autoencoder-Based Anomaly Detectors to Adversarial Poisoning Attacks
Authors: Moshe Kravchik, Asaf Shabtai | Published: 2020-02-07
Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance
Authors: Farhad Farokhi | Published: 2020-01-29
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Authors: Xuanqing Liu, Si Si, Xiaojin Zhu, Yang Li, Cho-Jui Hsieh | Published: 2019-10-30