@inproceedings{a248d0c631c8466686bd5800107ab782,
title = "Intrusion Detection based on Non-negative Positive-unlabeled Learning",
abstract = "Due to the diversity of network traffic flow, intrusion detection is usually studied as an anomaly detection problem. In this paper, Positive-unlabeled with Non-negative Risk Estimator(nnPU) learning is introduced for intrusion detection. The cyber attacks is treated as positive samples in PU learning. A risk estimator is raised to estimates the binary classification loss. For data imbalance in intrusion detection, we improve the risk estimator of nnPU through focal loss(FL-nnPU). The dynamic weights in focal loss is used to balance the small class prior. The experiments result show that FL-nnPU have a close performance to binary classification, and it performs better than nnPU under data imbalance problems.",
keywords = "data imbalance, intrusion detection, positive-unlabeled learning, risk estimator",
author = "Sicai Lv and Yang Liu and Zhiyao Liu and Wang Chao and Chenrui Wu and Bailing Wang",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 9th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2020 ; Conference date: 20-11-2020 Through 22-11-2020",
year = "2020",
month = nov,
day = "20",
doi = "10.1109/DDCLS49620.2020.9275048",
language = "英语",
series = "Proceedings of 2020 IEEE 9th Data Driven Control and Learning Systems Conference, DDCLS 2020",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1015--1020",
editor = "Mingxuan Sun and Huaguang Zhang",
booktitle = "Proceedings of 2020 IEEE 9th Data Driven Control and Learning Systems Conference, DDCLS 2020",
address = "美国",
}