AI engineering glossary · Evals guardrails AI security
What is adversarial robustness?
Adversarial robustness (also called robustness): How well a model keeps giving correct outputs when inputs are deliberately perturbed by an attacker. It is measured as accuracy under specified attacks and perturbation limits, and differs from ordinary generalisation to new but natural data.
Adversarial robustness: an example
A classifier scores 95 percent on clean images but 40 percent when each pixel may be changed by a small bound, so its robustness is 40 percent.
Related terms
More Evals guardrails AI security terms
- Adversarial suffix
- Adversarial test set
- Adversarial training
- Answer relevancy
- Attack success rate
- Attack surface
- Automated red teaming
- Backdoor attack
Where you learn it
Adversarial robustness is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.