UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
This provides a universal and automated solution for certified robustness in adversarial machine learning, addressing a broad and critical security issue.
The paper tackles the problem of certifying robustness of machine learning classifiers against adversarial perturbations by proposing UniCR, a universally approximated certified robustness framework that can approximate robustness for any input, classifier, ℓ_p perturbations, and continuous noise distribution, achieving state-of-the-art results in experiments.
We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate the robustness certification of any input on any classifier against any $\ell_p$ perturbations with noise generated by any continuous probability distribution. Compared with the state-of-the-art certified defenses, UniCR provides many significant benefits: (1) the first universal robustness certification framework for the above 4 'any's; (2) automatic robustness certification that avoids case-by-case analysis, (3) tightness validation of certified robustness, and (4) optimality validation of noise distributions used by randomized smoothing. We conduct extensive experiments to validate the above benefits of UniCR and the advantages of UniCR over state-of-the-art certified defenses against $\ell_p$ perturbations.