Название: Machine Learning for Cyber Security Автор: Xiaofeng Chen, Xinyi Huang
Издательство: Springer
Год: 2019
Страниц: 410
Язык: английский
Формат: pdf (true)
Размер: 35.23 MB
This book constitutes the proceedings of the Second International Conference on Machine Learning for Cyber Security, ML4CS 2019, held in Xi’an, China in September 2019.
The 23 revised full papers and 3 short papers presented were carefully reviewed and selected from 70 submissions. The papers detail all aspects of machine learning in network infrastructure security, in network security detections and in application software security.
Cyber security has become the most crucially important topic for safeguarding national and personal safety. Achieving cyber security depends not only on defense technologies, but also the technologies to detect and discover cyber intrusions, threats and attacks. Herein, network data plays an essential role. However, network data for security detection (i.e., security-related data) normally features big data characters. How to collect and process them in an efficient, effective and precise way becomes a big challenge towards network security measurement. In this book, I will introduce the current research results of my research team in terms of adaptive network data collection in heterogenous networks, data fusion and compression for highly efficient network intrusion detection and economic data storage, a method of application-layer tunnel detection with rules and machine learning, as well as data mining and analytics on opinions posted in the website for retrieving trust information and generating reputation. Working on security-related network data collection, fusion, mining and analytics, we make efforts to collect and process as few as possible data in a context-aware manner, but achieve as accurate as possible security detection results.
There are challenges and issues when Machine Learning algorithm needs to access highly sensitive data for the training process. In order to address these issues, several privacy-preserving Deep Learning techniques, including Secure Multi-Party Computation and Homomorphic Encryption in Neural Network have been developed. There are also several methods to modify the Neural Network, so that it can be used in privacy-preserving environment. However, there is trade-off between privacy and performance among various techniques. In this paper, we discuss state-of-the-art of Privacy-Preserving Deep Learning, evaluate all methods, compare pros and cons of each approach, and address challenges and issues in the field of privacy-preserving by Deep Learning.
Contents:
Скачать Machine Learning for Cyber Security