Adversarial Examples as an Input-Fault Tolerance Problem
- University of Guelph（圭尔夫大学）
- Vector Institute for Artificial Intelligence（向量人工智能研究所）
- University of Waterloo（滑铁卢大学）
- Perimeter Institute for Theoretical Physics（圆周理论物理研究所）
机构由 AI 辅助整理，请以论文原文为准。
更新
英文摘要：
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., $ε$-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse input faults.
