Poisoning Retrieval Corpora by Injecting Adversarial Passages
Top Cited Papers
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 13764-13775
Abstract
Zexuan Zhong, Ziqing Huang, Alexander Wettig, Danqi Chen. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Order-Disorder2022
- Simple Entity-Centric Questions Challenge Dense Retrievers2021
- Universal Adversarial Attacks with Natural Triggers for Text Classification2021
- BERT-ATTACK: Adversarial Attack Against BERT Using BERT2020
- Adversarial Semantic Collisions2020
- Dense Passage Retrieval for Open-Domain Question Answering2020
- TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP2020
- SPECTER: Document-level Representation Learning using Citation-informed Transformers2020
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- WWW'18 Open Challenge2018