Weight Poisoning Attacks on Pre-trained Models
Authors: Keita Kurita, Paul Michel, Graham Neubig | Published: 2020-04-14
バックドア攻撃
MetaPoison: Practical General-purpose Clean-label Data Poisoning
Authors: W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein | Published: 2020-04-01 | Updated: 2021-02-21
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
Authors: Xuezhou Zhang, Yuzhe Ma, Adish Singla, Xiaojin Zhu | Published: 2020-03-27 | Updated: 2020-06-22
RAB: Provable Robustness Against Backdoor Attacks
Authors: Maurice Weber, Xiaojun Xu, Bojan Karlaš, Ce Zhang, Bo Li | Published: 2020-03-19 | Updated: 2023-08-03
Towards Probabilistic Verification of Machine Unlearning
Authors: David Marco Sommer, Liwei Song, Sameer Wagh, Prateek Mittal | Published: 2020-03-09 | Updated: 2020-12-01
Towards Backdoor Attacks and Defense in Robust Machine Learning Models
Authors: Ezekiel Soremekun, Sakshi Udeshi, Sudipta Chattopadhyay | Published: 2020-02-25 | Updated: 2023-01-11
Label-Consistent Backdoor Attacks
Authors: Alexander Turner, Dimitris Tsipras, Aleksander Madry | Published: 2019-12-05 | Updated: 2019-12-06
Deep Probabilistic Models to Detect Data Poisoning Attacks
Authors: Mahesh Subedar, Nilesh Ahuja, Ranganath Krishnan, Ibrahima J. Ndiour, Omesh Tickoo | Published: 2019-12-03
Failure Modes in Machine Learning Systems
Authors: Ram Shankar Siva Kumar, David O Brien, Kendra Albert, Salomé Viljöen, Jeffrey Snover | Published: 2019-11-25
Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statistic
Authors: Zhen Xiang, David J. Miller, Hang Wang, George Kesidis | Published: 2019-11-18 | Updated: 2020-04-06