Walking the Embedding Space: Datastore Extraction from Multimodal RAG

Name: Walking the Embedding Space: Datastore Extraction from Multimodal RAG
Uploaded: 2026-10-05T07:45:18.397134+00:00
Duration: 620 s
Description: Researchers developed imMRAG, an adaptive attack targeting image-returning retrieval systems. This method uses relevance-weighted resampling to systematically explore embedding spaces, allowing an attacker to extract significant amounts of data—up to 611 images in one run. The findings emphasize that the image channel is a powerful vector for malicious instruction delivery.

Researchers developed imMRAG, an adaptive attack targeting image-returning retrieval systems. This method uses relevance-weighted resampling to systematically explore embedding spaces, allowing an attacker to extract significant amounts of data—up to 611 images in one run. The findings emphasize that the image channel is a powerful vector for malicious instruction delivery.

Open the full episode