Adversarial Examples as an Input-Fault Tolerance Problem

Autor:	Galloway, Angus, Golubeva, Anna, Taylor, Graham W.
Rok vydání:	2018
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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., $\epsilon$-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse input faults. Comment: NIPS 2018 Workshop on Security and Machine Learning. Source available at https://github.com/uoguelph-mlrg/nips18-secml-advex-input-fault
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1811.12601 Zobrazit plný text záznamu View this record from Arxiv