Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914358679830528 |
|---|---|
| author | Edemacu, Kennedy Shokri, Mohammad Mahdi |
| author_facet | Edemacu, Kennedy Shokri, Mohammad Mahdi |
| contents | Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses in external, factual knowledge and thus mitigating hallucinations. However, the integration of externally sourced knowledge bases introduces a critical attack surface. Adversaries can inject malicious multimodal content capable of influencing both retrieval and downstream generation. In this work, we present MM-MEPA, a multimodal poisoning attack that targets the metadata components of image-text entries while leaving the associated visual content unaltered. By only manipulating the metadata, MM-MEPA can still steer multimodal retrieval and induce attacker-desired model responses. We evaluate the attack across multiple benchmark settings and demonstrate its severity. MM-MEPA achieves an attack success rate of up to 91\% consistently disrupting system behaviors across four retrievers and two multimodal generators. Additionally, we assess representative defense strategies and find them largely ineffective against this form of metadata-only poisoning. Our findings expose a critical vulnerability in multimodal RAG and underscore the urgent need for more robust, defense-aware retrieval and knowledge integration methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00172 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation Edemacu, Kennedy Shokri, Mohammad Mahdi Cryptography and Security Artificial Intelligence Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses in external, factual knowledge and thus mitigating hallucinations. However, the integration of externally sourced knowledge bases introduces a critical attack surface. Adversaries can inject malicious multimodal content capable of influencing both retrieval and downstream generation. In this work, we present MM-MEPA, a multimodal poisoning attack that targets the metadata components of image-text entries while leaving the associated visual content unaltered. By only manipulating the metadata, MM-MEPA can still steer multimodal retrieval and induce attacker-desired model responses. We evaluate the attack across multiple benchmark settings and demonstrate its severity. MM-MEPA achieves an attack success rate of up to 91\% consistently disrupting system behaviors across four retrievers and two multimodal generators. Additionally, we assess representative defense strategies and find them largely ineffective against this form of metadata-only poisoning. Our findings expose a critical vulnerability in multimodal RAG and underscore the urgent need for more robust, defense-aware retrieval and knowledge integration methods. |
| title | Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.00172 |