Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
Authors: Xi Li, Ruofan Mao, Yusen Zhang, Renze Lou, Chen Wu, Jiaqi Wang | Published: 2024-06-10 | Updated: 2025-10-30
トリガーの検知
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Authors: Chengkun Wei, Wenlong Meng, Zhikun Zhang, Min Chen, Minghu Zhao, Wenjing Fang, Lei Wang, Zihui Zhang, Wenzhi Chen | Published: 2023-08-26 | Updated: 2023-10-14
WW-FL: Secure and Private Large-Scale Federated Learning
Authors: Felix Marx, Thomas Schneider, Ajith Suresh, Tobias Wehrle, Christian Weinert, Hossein Yalame | Published: 2023-02-20 | Updated: 2025-10-14
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
Authors: Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, Maosong Sun | Published: 2020-11-20 | Updated: 2021-11-03
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
Authors: Aditya Golatkar, Alessandro Achille, Stefano Soatto | Published: 2019-11-12 | Updated: 2020-03-31
Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
Authors: Bao Gia Doan, Ehsan Abbasnejad, Damith C. Ranasinghe | Published: 2019-08-09 | Updated: 2020-09-28
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks
Authors: Francesco Croce, Jonas Rauber, Matthias Hein | Published: 2019-03-27 | Updated: 2019-09-25
STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
Authors: Yansong Gao, Chang Xu, Derui Wang, Shiping Chen, Damith C. Ranasinghe, Surya Nepal | Published: 2019-02-18 | Updated: 2020-01-17
Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
Authors: Priyadarshini Panda, Indranil Chakraborty, Kaushik Roy | Published: 2019-02-08 | Updated: 2019-02-11
Universal Rules for Fooling Deep Neural Networks based Text Classification
Authors: Di Li, Danilo Vasconcellos Vargas, Sakurai Kouichi | Published: 2019-01-22 | Updated: 2019-04-03