论文标题
部分可观测时空混沌系统的无模型预测
MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples
论文作者
论文摘要
多标签分类预测输入的一组标签，具有许多应用程序。但是，最近的多项研究表明，多标签分类容易受到对抗例子的影响。尤其是，攻击者可以通过向其添加精心制作的人类侵蚀性扰动来操纵由多标签分类器预测的标签。当对多标签分类概括时，现有的多类分类的可证明的防御能力可实现次优的鲁棒性。在这项工作中，我们提出了MultiGuard，这是第一个针对多标签分类的对抗性例子的强大防御。我们的多物种利用随机的平滑度，这是构建可证明强大分类器的最新技术。具体而言，给定任意多标签分类器，我们的多群岛通过向输入添加随机噪声来构建平滑的多标签分类器。我们考虑在这项工作中的各向同性高斯噪声。我们的主要理论贡献是，当$ \ ell_2 $ - 添加到输入中的对抗性扰动的$ \ ell_2 $ norm时，我们表明，输入的一定数量的地面真相标签被证明是在我们的多g预测的一组标签中。此外，我们设计了一种算法来计算我们可证明的鲁棒性保证。从经验上讲，我们评估了我们在VOC 2007，MS-Coco和NUS范围内基准数据集的多目标。我们的代码可在：\ url {https://github.com/quwenjie/multiguard}中找到
Multi-label classification, which predicts a set of labels for an input, has many applications. However, multiple recent studies showed that multi-label classification is vulnerable to adversarial examples. In particular, an attacker can manipulate the labels predicted by a multi-label classifier for an input via adding carefully crafted, human-imperceptible perturbation to it. Existing provable defenses for multi-class classification achieve sub-optimal provable robustness guarantees when generalized to multi-label classification. In this work, we propose MultiGuard, the first provably robust defense against adversarial examples to multi-label classification. Our MultiGuard leverages randomized smoothing, which is the state-of-the-art technique to build provably robust classifiers. Specifically, given an arbitrary multi-label classifier, our MultiGuard builds a smoothed multi-label classifier via adding random noise to the input. We consider isotropic Gaussian noise in this work. Our major theoretical contribution is that we show a certain number of ground truth labels of an input are provably in the set of labels predicted by our MultiGuard when the $\ell_2$-norm of the adversarial perturbation added to the input is bounded. Moreover, we design an algorithm to compute our provable robustness guarantees. Empirically, we evaluate our MultiGuard on VOC 2007, MS-COCO, and NUS-WIDE benchmark datasets. Our code is available at: \url{https://github.com/quwenjie/MultiGuard}
