<object id="cn0w2"><option id="cn0w2"></option></object>
  • <thead id="cn0w2"><del id="cn0w2"></del></thead>
  • <object id="cn0w2"></object>
  • 網絡空間安全學院
    綜合通知
    學術報告:基于CNN隱寫分析及對抗嵌入隱寫的博弈理論框架
    作者:  來源:網絡空間安全學院  時間:2019-04-24  點擊量:10

    【學術報告】:基于CNN隱寫分析及對抗嵌入隱寫的博弈理論框架

    【報告人】:李斌

    【地 點】:科技館3338會議室

    【時 間】:2019426日(星期五) 1000~11:00

    【報告人介紹】

    Dr. Bin Li received the Ph.D. degree in communication and information system from Sun Yat-sen University, Guangzhou, China, in 2009. He was a Visiting Scholar with New Jersey Institute of Technology, Newark, NJ, USA, from 2007 to 2008. He is currently a research scholar, associate professor, and Ph.D. supervisor with Shenzhen University, Shenzhen, China. He has been awarded three grants from NSFC and co-authored more than 40 IEEE journal and conference papers. Now he is the director of Shenzhen Key Laboratory of Media Security, a member of IEEE Information Forensic and Security Technical Committee (IFS-TC), vice president of Guangdong Society of Image and Graphics. His current research interests include image processing, multimedia forensics, and pattern recognition.

    【報告內容簡介】

      圖像隱寫與隱寫分析是信息隱藏的主要研究方向。近年來,基于CNN的隱寫分析在檢測內容自適應圖像隱寫方面取得了不錯的進展。而利用對抗樣本技術,隱寫方也可以采用對抗嵌入策略有效對抗基于CNN的隱寫分析。通常而言,隱寫分析方不能獲知隱寫方所采用的對抗嵌入的參數。同理,隱寫方也未必能確知隱寫分析方所用的參數。對于該信息的缺失,我們提出一種基于博弈理論模型的解決方案,分析隱寫系統的安全性。我們的分析表明,在此模型下,非零和的博弈可以轉化為零和博弈,有利于降低尋找均衡點的復雜性。此外,利用該博弈模型的結論,可以增加隱寫分析檢測的可靠性。

     

     

    歡迎廣大師生參加!


    秒速赛车前5后5计划