Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
Authors: Hossein Souri, Liam Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein | Published: 2021-06-16 | Updated: 2022-10-13
バックドア攻撃
Stealthy Backdoors as Compression Artifacts
Authors: Yulong Tian, Fnu Suya, Fengyuan Xu, David Evans | Published: 2021-04-30
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
Authors: Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh | Published: 2021-04-22
Adversarial Training for Deep Learning-based Intrusion Detection Systems
Authors: Islam Debicha, Thibault Debatty, Jean-Michel Dricot, Wim Mees | Published: 2021-04-20
Defending Against Adversarial Denial-of-Service Data Poisoning Attacks
Authors: Nicolas M. Müller, Simon Roschmann, Konstantin Böttinger | Published: 2021-04-14 | Updated: 2021-11-30
Black-box Detection of Backdoor Attacks with Limited Information and Data
Authors: Yinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu | Published: 2021-03-24
TAD: Trigger Approximation based Black-box Trojan Detection for AI
Authors: Xinqiao Zhang, Huili Chen, Farinaz Koushanfar | Published: 2021-02-03 | Updated: 2021-04-20
Fast Training of Provably Robust Neural Networks by SingleProp
Authors: Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel | Published: 2021-02-01
Active Learning Under Malicious Mislabeling and Poisoning Attacks
Authors: Jing Lin, Ryan Luley, Kaiqi Xiong | Published: 2021-01-01 | Updated: 2021-09-02
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Authors: Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein | Published: 2020-12-18 | Updated: 2021-03-31