ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models
Authors: Jin Xie, Ruishi He, Songze Li, Xiaojun Jia, Shouling Ji | Published: 2025-04-29
バックドアモデルの検知
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
Authors: Yechao Zhang, Yuxuan Zhou, Tianyu Li, Minghui Li, Shengshan Hu, Wei Luo, Leo Yu Zhang | Published: 2025-04-16
ToxicSQL: Migrating SQL Injection Threats into Text-to-SQL Models via Backdoor Attack
Authors: Meiyu Lin, Haichuan Zhang, Jiale Lao, Renyuan Li, Yuanchun Zhou, Carl Yang, Yang Cao, Mingjie Tang | Published: 2025-03-07 | Updated: 2025-04-03
ExpShield: Safeguarding Web Text from Unauthorized Crawling and Language Modeling Exploitation
Authors: Ruixuan Liu, Toan Tran, Tianhao Wang, Hongsheng Hu, Shuo Wang, Li Xiong | Published: 2024-12-30 | Updated: 2025-05-07
Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
Authors: Ye Li, Yanchao Zhao, Chengcheng Zhu, Jiale Zhang | Published: 2024-09-29 | Updated: 2025-03-22
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
Authors: Giorgio Severi, Simona Boboila, John Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Michael J. De Lucia, Alina Oprea | Published: 2024-07-11 | Updated: 2025-05-05
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Authors: Shuai Zhao, Leilei Gan, Luu Anh Tuan, Jie Fu, Lingjuan Lyu, Meihuizi Jia, Jinming Wen | Published: 2024-02-19 | Updated: 2024-03-29
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
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Authors: Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K. Reddy, Bimal Viswanath | Published: 2021-03-07 | Updated: 2021-03-11
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