题 目：媒体取证与对抗网络的应用

报告人：David Doermann  Professor，IEEE and IAPR fellow

时 间：2020年1月6日（周一）14：00

地 点：青山湖校区（北）软件楼222

报告人简介：

Dr. David Doermann is a  Professor of Empire Innovation at the University at  Buffalo (UB). David is a leading  research  and innovative  thinker in  the  areas of  document  image analysis and recognition. He and his  group of researchers  focused  on many  innovative topics  related to analysis  and processing  of document  images  and video  including triage, visual indexing and retrieval, enhancement and recognition of both textual  and structural  components of visual media. David has over 250  publications in conferences and journals, is a fellow of the IEEE and IAPR,has numerous awards including an honorary doctorate from the University of Oulu,Finland  and is a founding Editor-in-Chief of the International Journal on DocumentAnalysis and Recognition.  

Tampering with or misrepresenting content in images and video is a concern for many groups.  The ability to create or  manipulate this  content, which  we  typically trust because we can “see” it, is becoming  more pervasive. Until recently, only high value media has been analyzed for integrity, often done by hand  and with adhoc tools.  While the research community has shown some progress in developing automated tools that indicate tampering, localize potential manipulations and document inconsistencies, they almost universally require human  judgement for decision  making.  This talk will first report on progress and lay out the successes and technical achievements.The second part of this talk will focus on the role of adversarial networks for both  hardening our algorithms,  and the threat  caused by their  ability  to automatically generate and modify content. He will overview these networks and give examples of how they are used in Media Forensics.Finally, he will provide some summary thoughts on how other Artificial Intelligence technologies are being applied and the challenges of trust, ethical behavior and security.

    欢迎广大师生参加！

软件学院

2020年1月2日