Skip to main content
    Skip to main contentSkip to navigationSkip to footer
    Artificial Intelligence

    Certified Defense

    Also known as:
    Provable Robustness
    Certified Robustness
    Verified Defense
    Updated: 2/11/2026

    Defense methods against adversarial attacks that provide mathematically provable robustness guarantees.

    Quick Summary

    Certified defenses provide mathematically provable guarantees that a model is robust against attacks within a defined perturbation radius.

    Explanation

    Certified defenses use randomized smoothing, abstract interpretation, or convex relaxation to prove that no perturbation within an ε-radius can change the prediction.

    Marketing Relevance

    For safety-critical AI applications (fraud detection, content moderation), certified defenses provide formal security guarantees.

    Example

    An image classifier proves that no ℓ₂ perturbation with ε<0.5 can change the result from "safe" to "unsafe".

    Common Pitfalls

    Certified defenses are compute-intensive and scale poorly to large models. Guarantees only apply to specific perturbation types.

    Origin & History

    Cohen et al. (2019) established randomized smoothing as a scalable certified defense. Wong & Kolter (2018) showed convex relaxation-based approaches. The field has expanded to LLM safety by 2025.

    Comparisons & Differences

    Certified Defense vs. Adversarial Training

    Adversarial training provides empirical robustness (can be broken); certified defenses provide formal, mathematical guarantees.

    Related Services

    Related Terms

    👋Questions? Chat with us!