Scientists poison their own data when it is stolen by an AI to destroy the results
Researchers from China and Singapore proposed AURA (Active Utility Reduction via Adulteration) to protect GraphRAG systems AURA deliberately poisons proprietary knowledge graphs so that stolen data produces hallucinations and incorrect responses Correct output requires a secret key; tests showed ~94% efficiency in breaking down stolen KG tools Researchers from universities in China and Singapore came […]
Scientists poison their own data when it is stolen by an AI to destroy the results Read More »








