AI engineering glossary · Evals guardrails AI security
What is FGSM (Fast Gradient Sign Method)?
Fast Gradient Sign Method (also called FGSM): A simple attack that creates an adversarial example in one step by nudging every input feature in the direction that increases the model's loss, using the sign of the gradient: x_adv = x + epsilon * sign(gradient of loss with respect to x).
Fast Gradient Sign Method: an example
With epsilon = 0.01, each pixel value is shifted by 0.01 up or down according to the gradient sign, changing the model's prediction.
Related terms
More Evals guardrails AI security terms
Where you learn it
Fast Gradient Sign Method is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.