演讲题目: 基于机器学习的入侵检测技术
演讲摘要:
Network intrusion detection is one of the most important parts for cyber security to protect computer systems against malicious attacks. With the emergence of numerous sophisticated and new attacks, however, network intrusion detection techniques are facing several sig- ni cant challenges. The overall objective of this study is to learn useful feature representations automatically and eciently from large amounts of unlabeled raw network trac data by using deep learning approaches.
We propose a novel network intrusion model by stacking dilated con- volutional autoencoders and evaluate our method on two new intru- sion detection datasets. Several experiments were carried out to check the e ectiveness of our approach. The comparative experimental results demonstrate that the proposed model can achieve considerably high per- formance which meets the demand of high accuracy and adaptability of network intrusion detection systems (NIDSs). It is quite potential and promising to apply our model in the large-scale and real-world network environments.
蔡志平教授简介:
蔡志平，国防科学技术大学计算机学院教授，博士生导师。现任中国计算机学会理论计算机专委会副秘书长、互联网专委委员、中国计算机学会高级会员。担任ToN等顶级期刊的审稿人和多个国际会议程序（组织）委员会委员，曾任加拿大多伦多大学和香港理工大学的访问教授。长期从事网络安全和大数据处理等领域的基础研究。负责国家自然科学基金项目3项（其中2项结题为优），其他项目5项，参与973项目、国防预研重点项目等多项科研工作。第一作者在IEEE Transactions on Computers等国际顶级期刊上和ICNP等国际一流会议上发表论文30多篇，共发表论文150多篇，其中SCI/EI检索80多篇次，被引用2000多次。授权国家发明专利5项，3次获得国际会议最佳论文奖。
龙军副教授简介:
龙军，国防科技大学计算机学院副教授，硕士生导师，博士。中国计算机学会高级会员，中国计算机学会理论计算机科学专委会委员。研究方向：机器学习，网络安全。国际学术会议MDAI 2011 大会主席，编辑国际学术论文集3部。承担和参与国家自然科学基金项目、863等科研项目10余项，发表SCI、EI论文30余篇。