7月10日萨姆休斯顿州立大学Qingzhong Liu博士学术报告预告

日期:2018/7/9
讲座题目:智能分析构建自动化网络安全威胁检测和防御体系
报告时间:2018年7月10日上午10:00
报告地点:信息楼A511会议室
报告人简介

Qingzhong Liu is currently an Associate Professor and one of core faculty members for the PhD program in Digital and Cyber Forensic Science (the sole such a Ph.D. program of the USA) in the Department of Computer Science, Sam Houston State University. He earned his Ph.D. degree in Computer Science from New Mexico Institute of Mining and Technology in 2007. His research interests include digital forensics, cyber security, bioinformatics, computing intelligence and applications. His study in multimedia forensics has been funded by the U.S. National Institute of Justice and by the U.S. National Science Foundation. He was the recipient of the “Fraud Impact Award” in Great Houston 2015 and the SHSU Excellence in Scholarly and Creative Activity Award in 2017. He has been serving on the Technical Program Committee of the ACM Workshop on Information Hiding and Multimedia Security since 2013. According to Google Scholar, his work has been cited over 2000 times.

报告摘要

While enormous digital multimedia data nowadays mostly enrich our everyday life, cyber terrorists and cyber criminals may use the data to conduct stealthy communication by using steganography, or alter the truth and make fraudulent illusions by forgery manipulation. To protect national security and public safety, multimedia forensics has emerged and developed in a rapid fashion; however, it still falls short of efficient and effective digital forensics algorithms and/or systems. Particularly, advanced steganography and advance forgery on multimedia data with combined attacks have severely impeded the progress in multimedia forensics. In this talk, we address a part of these challenges, we introduce our work in steganalysis and forgery detection on multimedia data, especially on image data. Image complexity will be discussed as a new metric to measure the detection performance. Hybrid large feature mining and ensemble learning will be introduced in detecting steganography, inpainting forgery, and seam carving forgery. The open problems in multimedia forensics will be discussed too.