Exploiting Instruction-Following Retrievers for Malicious Information Retrieval
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917951733497856 |
|---|---|
| author | BehnamGhader, Parishad Meade, Nicholas Reddy, Siva |
| author_facet | BehnamGhader, Parishad Meade, Nicholas Reddy, Siva |
| contents | Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the safety risks surrounding their increasing search capabilities. We empirically study the ability of retrievers to satisfy malicious queries, both when used directly and when used in a retrieval augmented generation-based setup. Concretely, we investigate six leading retrievers, including NV-Embed and LLM2Vec, and find that given malicious requests, most retrievers can (for >50% of queries) select relevant harmful passages. For example, LLM2Vec correctly selects passages for 61.35% of our malicious queries. We further uncover an emerging risk with instruction-following retrievers, where highly relevant harmful information can be surfaced by exploiting their instruction-following capabilities. Finally, we show that even safety-aligned LLMs, such as Llama3, can satisfy malicious requests when provided with harmful retrieved passages in-context. In summary, our findings underscore the malicious misuse risks associated with increasing retriever capability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08644 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploiting Instruction-Following Retrievers for Malicious Information Retrieval BehnamGhader, Parishad Meade, Nicholas Reddy, Siva Computation and Language Artificial Intelligence Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the safety risks surrounding their increasing search capabilities. We empirically study the ability of retrievers to satisfy malicious queries, both when used directly and when used in a retrieval augmented generation-based setup. Concretely, we investigate six leading retrievers, including NV-Embed and LLM2Vec, and find that given malicious requests, most retrievers can (for >50% of queries) select relevant harmful passages. For example, LLM2Vec correctly selects passages for 61.35% of our malicious queries. We further uncover an emerging risk with instruction-following retrievers, where highly relevant harmful information can be surfaced by exploiting their instruction-following capabilities. Finally, we show that even safety-aligned LLMs, such as Llama3, can satisfy malicious requests when provided with harmful retrieved passages in-context. In summary, our findings underscore the malicious misuse risks associated with increasing retriever capability. |
| title | Exploiting Instruction-Following Retrievers for Malicious Information Retrieval |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.08644 |