Skip to main content
Home/Risks/Schnitzer2024/Data poisoning

Data poisoning

Category
Risk Domain

Vulnerabilities that can be exploited in AI systems, software development toolchains, and hardware, resulting in unauthorized access, data and privacy breaches, or system manipulation causing unsafe outputs or behavior.

"Data poisoning describes an attack in the form of an injection of malicious data into the training set. If not prevented, this attack leads the AI system to learn unintended behavior."(p. 9)

Other risks from Schnitzer2024 (24)