Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 8116-8134
Abstract
Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor LearningInternational Journal of Computer Vision, 2025
- NCL: Textual Backdoor Defense Using Noise-Augmented Contrastive Learning2023
- Backdoor Defense via Deconfounded Representation Learning2023
- Piccolo: Exposing Complex Backdoors in NLP Transformer Models2022
- BDDR: An Effective Defense Against Textual Backdoor AttacksComputers & Security, 2021
- Mitigating backdoor attacks in LSTM-based text classification systems by Backdoor Keyword IdentificationNeurocomputing, 2021
- Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural NetworksIEEE Transactions on Dependable and Secure Computing, 2021
- A Backdoor Attack Against LSTM-Based Text Classification SystemsIEEE Access, 2019
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks2018
- A Memory-Based Approach to Anti-Spam Filtering for Mailing ListsInformation Retrieval Journal, 2003