DisarmRAG: Stealthy Retriever Poisoning to Disable Self-Correction in Retrieval-Augmented Generation
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4627-4641
Abstract
No abstract availableThis publication has 23 references indexed in Scilit:
- BadMerging: Backdoor Attacks Against Model Merging2024
- PMET: Precise Model Editing in a TransformerProceedings of the AAAI Conference on Artificial Intelligence, 2024
- MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection2023
- Synthetic Disinformation Attacks on Automated Fact Verification SystemsProceedings of the AAAI Conference on Artificial Intelligence, 2022
- A Survey on Multi-Task LearningIEEE Transactions on Knowledge and Data Engineering, 2021
- SimCSE: Simple Contrastive Learning of Sentence Embeddings2021
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009
- Reciprocal rank fusion outperforms condorcet and individual rank learning methods2009