Backdoor Attacks on Dense Passage Retrievers for Disseminating Misinformation

arXiv:2402.13532v1 Announce Type: new
Abstract: Dense retrievers and retrieval-augmented language models have been widely used in various NLP applications. Despite being designed to deliver reliable and secure outcomes, the vulnerability of retrievers to potential attacks remains unclear, raising concerns about their security. In this paper, we introduce a novel scenario where the attackers aim to covertly disseminate targeted misinformation, such as hate speech or advertisement, through a retrieval system. To achieve this, we propose a perilous backdoor attack triggered by …

abstract applications arxiv attacks backdoor concerns cs.cl language language models misinformation nlp novel paper retrieval retrieval-augmented security type vulnerability