AI engineering glossary · Evals guardrails AI security
What is adversarial training?
Adversarial training: A defence that improves a model's resistance to attacks by including adversarial examples, generated on the fly, in its training data so it learns to classify them correctly. It usually costs more compute and can slightly lower accuracy on clean inputs.
Adversarial training: an example
At each training step, the team perturbs the batch with FGSM and trains on both clean and perturbed images.
Related terms
More Evals guardrails AI security terms
- Answer relevancy
- Attack success rate
- Attack surface
- Automated red teaming
- Backdoor attack
- Benchmark saturation
- Canary token
- Chatbot Arena
Where you learn it
Adversarial training is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.