Semantic Adversarial Deep Learning

Semantic Adversarial Deep Learning
复制标题

DOI:
10.1109/mdat.2020.2968274
复制
发表时间:
2018-04
期刊:
影响因子:
2
通讯作者:
S. Seshia;S. Jha;T. Dreossi
S. Seshia;S. Jha;T. Dreossi
中科院分区:
工程技术4区
文献类型:
--
作者:
S. Seshia;S. Jha;T. Dreossi

文献摘要

相似文献

对抗性示例已经成为基于机器学习的系统的一个关键威胁,特别是那些使用深度神经网络的系统。与该领域的大量研究不同,这篇Keynote文章解释了资源受限环境中具有机器学习组件的完整系统的语义、上下文和规范。-Muhammad Shafique,维也纳工业大学
Adversarial examples have emerged as a key threat for machine-learning-based systems, especially the ones that employ deep neural networks. Unlike a large body of research in this area, this Keynote article accounts for the semantic, context, and specifications of the complete system with machine learning components in resource-constrained environments. —Muhammad Shafique, Technische Universität Wien