報告題目：Data-Driven Cyber Security
主講嘉賓：Prof. Yang Xiang（項陽） Swinburne University of Technology（澳大利亞斯威本科技大學）
邀請人：張勇老師、張鵬老師
時間：2017年6月29日9:00-10:00
地點：科技樓1504
報告摘要: Today we have evidenced massive cyber attacks having hit millions of people in more than 150 countries with billions of dollars lose. Cyber security has become one of the top priorities in the research and development agenda globally.
In the big data era, we face a diversity of datasets from a uge number of sources in different domains. These datasets consist of multiple modalities, each of which has a different representation, distribution, scale, and density.
It has been widely recognized that the power of knowledge from multiple disparate (but potentially connected) datasets is paramount. For example, collecting multiple sources of information from online social networks has become common exercise to deal with social security problems.
Big data analytics are some of the most effective defenses against cyber intrusions. Better, faster, actionable security information reduces the critical time from detection to remediation, enabling cyber warfare specialists to proactively defend and protect cyberspace.
New methods and tools, consequently, must follow up in order to adapt to this emerging security paradigm. In this talk, we will discuss the concept of Data-Driven Cyber Security and how big data analytics can be used to address the security and privacy problems in cyberspace.
報告人簡介：Professor Yang Xiang received his PhD in Computer Science from Deakin University, Australia. He is now the Dean of Digital Research at Swinburne University of Technology.
. His research interests include network and system security, distributed systems, and data analytics. He has published more than 200 research papers in international journals and conferences, such as IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Information Security and Forensics, and IEEE Journal on Selected Areas in Communications. He serves as the Associate Editor of IEEE Transactions on Computers, IEEE Transactions on Parallel and Distributed Systems, Security and Communication Networks (Wiley), and the Editor of Journal of Network and Computer Applications (Elsevier). He is a Senior Member of the IEEE.
============================================================
報告題目：A Constrained Clustering Approach for Network Traffic Classification
主講嘉賓：Dr. Yu Wang（王宇） Deakin University(澳大利亞迪肯大學)
邀請人：張勇老師、張鵬老師
時間：2017年6月29日10:00-11:00
地點：科技樓1504
報告摘要：
Statistics-based Internet traffic classification using machine learning techniques has attracted extensive research interests lately, because of the increasing ineffectiveness of traditional port-based and payload-based approaches. In particular, unsupervised learning, i.e. traffic clustering, is very important in real-life applications, where labelled training data are difficult to obtain and new patterns keep emerging. Although previous studies have applied some classic clustering algorithms such as K-Means and EM for the task, the quality of resultant traffic clusters was far from satisfactory. In order to improve the accuracy of traffic clustering, we propose a constrained clustering scheme that makes decisions with consideration of some background information in addition to the observed traffic statistics. In this talk, I will introduce the approach in detail. Specifically, we make use of equivalence set constraints indicating that particular sets of flows are using the same application layer protocols, which can be efficiently inferred from packet headers according to the background knowledge of TCP/IP networking. We model the observed data and constraints using Gaussian mixture density and adapt an approximate algorithm for the maximum likelihood estimation of model parameters. Moreover, we will discuss the effects of unsupervised feature discretization on traffic clustering by using a fundamental binning method. A number of real-world Internet traffic traces have been used for evaluation, and the results presented here will show that the proposed approach not only improves the quality of traffic clusters in terms of overall accuracy and per-class metrics, but also speeds up the convergence.
報告人簡介：王宇， 2013年在澳大利亞迪肯大學網(wǎng)絡安全與計算實驗室獲得計算機科學博士，目前留校從事研究工作。主要的研究領域包括網(wǎng)絡流量建模與分類、社交網(wǎng)絡安全、網(wǎng)絡和系統(tǒng)安全、機器學習等方面。
