论文标题
捍卫基于黑盒骨架的人类活动分类器
Defending Black-box Skeleton-based Human Activity Classifiers
论文作者
论文摘要
骨骼运动已得到大量回应，以识别人类活动（HAR）。最近，在各种分类器和数据中都发现了基于骨架的HAR的普遍脆弱性，要求缓解。为此，我们为我们的最佳知识提出了第一种基于骨架的HAR的黑盒防御方法。我们的方法以清洁数据，对手和分类器的完整贝叶斯处理为特征，从而导致（1）新的基于贝叶斯能量的鲁棒分类器的配方，（2）基于自然运动歧管的新对手抽样方案，以及（3）新的Train Baster bayesian Bayesian Bashesian Black Boxs Defertain。我们将基于贝叶斯能量的对抗训练或节拍命名。 Beat直接但优雅，这将脆弱的黑盒分类器变成了强大的，而无需牺牲准确性。在各种攻击下，它在广泛的骨骼HAR分类器和数据集中表现出令人惊讶和普遍的有效性。代码可在https://github.com/realcrane/robustactionRecogniser上找到。
Skeletal motions have been heavily replied upon for human activity recognition (HAR). Recently, a universal vulnerability of skeleton-based HAR has been identified across a variety of classifiers and data, calling for mitigation. To this end, we propose the first black-box defense method for skeleton-based HAR to our best knowledge. Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense. We name our framework Bayesian Energy-based Adversarial Training or BEAT. BEAT is straightforward but elegant, which turns vulnerable black-box classifiers into robust ones without sacrificing accuracy. It demonstrates surprising and universal effectiveness across a wide range of skeletal HAR classifiers and datasets, under various attacks. Code is available at https://github.com/realcrane/RobustActionRecogniser.
