论文标题
表征多标签分类器的弹性攻击性
Characterizing the Evasion Attackability of Multi-label Classifiers
论文作者
论文摘要
多标签学习系统中的逃避攻击是一个有趣的，广泛见证的，但很少探索的研究主题。表征确定多标签对抗威胁的攻击性的关键因素是解释对抗性脆弱性的起源并了解如何减轻它的关键。我们的研究灵感来自对抗性风险束缚的理论。我们将目标多标签分类器的攻击性与分类器的规律性和培训数据分布相关联。除了理论攻击性分析之外，我们还通过贪婪的标签空间探索进一步提出了有效的经验攻击性估计器。它提供了可证明的计算效率和近似准确性。对现实世界数据集的实验结果验证了已公开的攻击性因素以及提议的经验攻击性指标的有效性
Evasion attack in multi-label learning systems is an interesting, widely witnessed, yet rarely explored research topic. Characterizing the crucial factors determining the attackability of the multi-label adversarial threat is the key to interpret the origin of the adversarial vulnerability and to understand how to mitigate it. Our study is inspired by the theory of adversarial risk bound. We associate the attackability of a targeted multi-label classifier with the regularity of the classifier and the training data distribution. Beyond the theoretical attackability analysis, we further propose an efficient empirical attackability estimator via greedy label space exploration. It provides provably computational efficiency and approximation accuracy. Substantial experimental results on real-world datasets validate the unveiled attackability factors and the effectiveness of the proposed empirical attackability indicator
