1. Mahdieh Abbasi and Christian Gagné. 2017. Robustness to adversarial examples through an ensemble of specialists. arXiv preprint arXiv:1702.06856(2017). Mahdieh Abbasi and Christian Gagné. 2017. Robustness to adversarial examples through an ensemble of specialists. arXiv preprint arXiv:1702.06856(2017).
2. Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
3. Philipp Benz Chaoning Zhang and In So Kweon. 2020. Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features. arxiv:2010.03316 [cs.LG] Philipp Benz Chaoning Zhang and In So Kweon. 2020. Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features. arxiv:2010.03316 [cs.LG]