论文标题
UNICR：通过随机平滑的普遍近似认证的鲁棒性
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
论文作者
论文摘要
我们研究机器学习分类器对对抗扰动的认证鲁棒性。特别是，我们提出了第一个普遍近似认证的鲁棒性（UNICR）框架，该框架可以近似于任何分类器上任何输入的鲁棒性认证，以与任何连续概率分布产生的噪声产生的任何$ \ ell_p $扰动。与最先进的认证防御措施相比，UNICR提供了许多重要的好处：（1）上述4'Any的第一个通用鲁棒性认证框架； （2）自动鲁棒性认证避免逐案分析，（3）认证鲁棒性的紧密验证以及（4）对随机平滑的噪声分布的最佳验证。我们进行了广泛的实验，以验证UNICR的上述好处以及UNICR对$ \ ell_p $扰动的最先进认证防御能力的优势。
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.
