6 min read
Research Research confirms that text embeddings stored in vector databases are not safely anonymised. Inversion attacks can reconstruct source text with high fidelity from embeddings alone, including those produced by commercial APIs.
Research confirms that text embeddings stored in vector databases are not safely anonymised. Inversion attacks can reconstruct source text with high fidelity from embeddings alone, including those produced by commercial APIs.
RAG pipelines introduce document poisoning, indirect prompt injection via retrieved content, and semantic access control gaps that most security teams have not assessed.