Spa-VLM crafts paired adversarial images and misleading texts to poison RAG-based VLM knowledge bases, reaching attack success rates above 0.8 with just five injected entries.
Opportunities for retrieval and tool augmented large language models in scientific facilities,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
Spa-VLM crafts paired adversarial images and misleading texts to poison RAG-based VLM knowledge bases, reaching attack success rates above 0.8 with just five injected entries.