AI Cybersecurity

#"AI #Cybersecurity" #by #Dr. #Meikang #Qiu #Professor #of #Computer #Science #from #Augusta #University
Share

In this talk, I will present a detailed research topic about AI Cybersecurity. Our group proposed an advanced gradient-based approach for mitigation of adversarial attacks in Deep Neural Networks (DNN).  The proposed approach adopted a random distortion transformation defense method called RDG (Random Distortion over Grids) and we combined it with non-linear defenses to thwart adversarial attacks. Extensive evaluation demonstrated the efficiency of this state-of-art defense approach.



  Date and Time

  Location

  Hosts

  Registration



  • Date: 17 Apr 2024
  • Time: 12:00 PM to 01:00 PM
  • All times are (GMT-05:00) US/Eastern
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • 1000 River Road
  • Teaneck , New Jersey
  • United States 07666
  • Building: Muscarelle Center, M105,
  • Room Number: M105

  • Contact Event Hosts
  • Co-sponsored by Fairleigh Dickinson University
  • Starts 21 February 2024 03:44 PM
  • Ends 17 April 2024 01:00 PM
  • All times are (GMT-05:00) US/Eastern
  • No Admission Charge


  Speakers

Dr. Meikang Qiu of Augusta University

Topic:

AI Cybersecurity

In this talk, I will present a detailed research topic about AI Cybersecurity. Our group proposed an advanced gradient-based approach for mitigation of adversarial attacks in Deep Neural Networks (DNN).  The proposed approach adopted a random distortion transformation defense method called RDG (Random Distortion over Grids) and we combined it with non-linear defenses to thwart adversarial attacks. Extensive evaluation demonstrated the efficiency of this state-of-art defense approach.

Biography:

Dr. Meikang Qiu received the BE and ME degrees from Shanghai Jiao Tong University and received a Ph.D. degree in Computer Science from the University of Texas at Dallas. Currently, He is a full professor at Augusta University. He is an ACM Distinguished Member. He is also the Highly Cited Researcher in 2021 from Web of Science and IEEE Distinguished Visitor in 2021-2023. He is the Chair of IEEE Smart Computing Technical Committee.  Till now his Google scholar citation is 23400+ and H-index 102.  His research interests include Cyber Security, AI, Big Data, Smarting Computing, Embedded systems, etc. He has published extensively in top conferences such as ACM CCS, ICML, IJCAI, DAC, and many IEEE/ACM Transactions. His paper on Tele-health system has won IEEE Systems Journal 2018 Best Paper Award.  His paper about data allocation for hybrid memory has been published in IEEE Transactions on Computers has been selected as IEEE TCSC 2016 Best Journal Paper and hot paper (1 in 1000 papers by Web of Science) in 2017. His paper published in IEEE Transactions on Computers about privacy protection for smart phones has been selected as a Highly Cited Paper in 2017-2020. He also won ACM Transactions on Design Automation of Electrical Systems (TODAES) 2011 Best Paper Award. He has won another 10+ Conference Best Paper Awards in recent years. 

Address:United States





Agenda

In this talk, I will present a detailed research topic about AI Cybersecurity. Our group proposed an advanced gradient-based approach for mitigation of adversarial attacks in Deep Neural Networks (DNN).  The proposed approach adopted a random distortion transformation defense method called RDG (Random Distortion over Grids) and we combined it with non-linear defenses to thwart adversarial attacks. Extensive evaluation demonstrated the efficiency of this state-of-art defense approach.