privacy

Researchers from Oxford and Meta demonstrate that four of five frontier LLMs exfiltrate sensitive data from multi-agent orchestrator systems via a single indirect prompt injection, bypassing access controls entirely.

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.

Training data can be reconstructed from foundation model weights with significantly higher accuracy than previously reported, with implications for GDPR compliance and IP protection.