Skip to main content
Home/Risks/IBM2025/Evasion attack

Evasion attack

Sub-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.

"Evasion attacks attempt to make a model output incorrect results by slightly perturbing the input data that is sent to the trained model."

Supporting Evidence (1)

1.
"Evasion attacks alter model behavior, usually to benefit the attacker."

Other risks from IBM2025 (63)