Randomized smoothing has recently emerged as an effective tool that enables certification of deep neural network classifiers at scale. All prior art on randomized smoothing has focused on isotropic $\ell_p$ certification, which has the advantage of yielding certificates that can be easily compared among isotropic methods via $\ell_p$-norm radius. However, isotropic certification limits the region that can be certified around an input to worst-case adversaries, i.e., it cannot reason about other "close", potentially large, constant prediction safe regions. To alleviate this issue, (i) we theoretically extend the isotropic randomized smoothing $\ell_1$ and $\ell_2$ certificates to their generalized anisotropic counterparts following a simplified analysis. Moreover, (ii) we propose evaluation metrics allowing for the comparison of general certificates - a certificate is superior to another if it certifies a superset region - with the quantification of each certificate through the volume of the certified region. We introduce ANCER, a framework for obtaining anisotropic certificates for a given test set sample via volume maximization. We achieve it by generalizing memory-based certification of data-dependent classifiers. Our empirical results demonstrate that ANCER achieves state-of-the-art $\ell_1$ and $\ell_2$ certified accuracy on CIFAR-10 and ImageNet in the data-dependence setting, while certifying larger regions in terms of volume, highlighting the benefits of moving away from isotropic analysis. Our code is available in https://github.com/MotasemAlfarra/ANCER.
翻译:最近,通过随机随机滑动,所有关于随机滑动的以往艺术都侧重于等离子(moell_ell_p$ p$)认证,其优点在于通过美元=ell_p$-norm 半径,在等离子(sotropic)方法之间容易进行比较的证书。然而,等离子认证限制了能够通过向最坏对手输入信息进行认证的区域,即,它不能说明其他“关闭”的潜在大、持续预测安全区域。为了缓解这一问题,(一)我们理论上将分流滑动的偏移($_ell_p$_p$_p$ p$_p$_pol_pal_protoprotographic 认证,在简化分析后,我们提出了允许比较一般证书的评估指标――如果它能验证一个超级区域,则无法通过认证区域的数量对每份证书进行量化。我们引入了ANCER,一个框架,为通过测试的正轨(rentral_ral_alalalalal-ralalalalalalalalalalalal) exligistralalal exal) exal exalial exalial exal exalial exal exal exalation,通过我们现有的数据在认证数据库中实现了常规数据质量-ral-ral-ral-ral-ral-rmaxxxxxxxxxxxxxxxxx。