Extraction attack risk for AI

Robustess Icon representing robustness risks.
Risks associated with input
Inference
Robustness
Amplified by generative AI

Description

An extraction attack attempts to copy or steal an AI model by appropriately sampling the input space and observing outputs to build a surrogate model that behaves similarly.

Why is extraction attack a concern for foundation models?

With a successful attack, the attacker can gain valuable information such as sensitive personal information or intellectual property.

Parent topic: AI risk atlas