Data Poisoning

An attack that corrupts a machine learning model by injecting malicious data into the training dataset, causing the model to learn incorrect patterns or exhibit targeted misbehaviour.

Sabotaging an AI by sneaking bad data into its training set. Like slipping wrong answers into a student's textbook; the AI learns incorrect things and makes mistakes later.

Data poisoning is a significant AI security risk that your governance framework must address. Data integrity controls, supply chain verification and ongoing monitoring are essential governance measures to protect against this threat.