BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230329T022716Z UID:792DADE0-3D1F-40A0-A3CF-99533B9882AC DTSTART;TZID=America/New_York:20230328T190000 DTEND;TZID=America/New_York:20230328T210000 DESCRIPTION:IEEE NJ Coast PACE SIGHT Group\, together with Computer Chapter and cosponsors present\n\nProfessor Dr Baek-Young Choi.\n\nTitle: The Eye s Have It\n\nAbstract: In this talk\, we will discuss how eyes can be used for liveness detection of mobile authentication and deepfake detection.\n \nAs the need for contactless biometric authentication becomes more signif icant during COVID-19 and beyond\, the popular biometric authentication me thod for mobile devices\, iris detection\, and facial recognition confront s various usability\, security\, and privacy concerns\, including mask-wea ring and various Presentation Attacks (PA). Specifically\, liveness detect ion against spoofed artifacts is one of the most challenging tasks as many existing methods cannot conclusively assess the user's physical presence in unsupervised environments. Even though several methods have been propos ed for tackling PA with motion challenges and 3D mapping\, most require ex pensive depth sensors and fail to detect sophisticated 3D reconstruction a ttacks. We present a software-based face PA Detection (PAD) method named\, which creates challenges and detects meaningful corneal specular reflecti on responses from human eyes. To detect human liveness\, our system genera tes multiple screen image patterns as a challenge\, then captures the resp onse of corneal specular reflections using a frontal camera and analyzes t he images using lightweight Machine Learning (ML) techniques. Liveness det ection system components include challenge pattern generation\, reflection image augmentation (e.g.\, super-resolution)\, and ML-based analyses. We have implemented the system as Android\, iOS\, and web apps. Our extensive experimental results show that our scheme achieves liveness detection wit h high accuracy at around 200 ms against various types of sophisticated PA s. The liveness detection can be applied for multiple contactless biometri c authentications accurately and efficiently without any costly extra sens ors nor involving users' active responses.\n\nThe second part is about dee pfake detection through eyes and environment. Deepfake techniques presenti ng AI-generated fictitious facial images of people can negatively influenc e the authenticity of online information. Starting as benign mesmerizing m emes\, they can be used malignantly to originate deception\, manipulation\ , persecution\, and seduction\, defying societal quality and human rights. However\, due to the recent development of sophisticated deepfake generat ion technologies\, it is getting harder to distinguish counterfeit images. Thus\, instead of relying on a single aspect of the visual features\, we detect various features from the specular reflection images such as color components\, shapes\, and textures to check the coordination with the surr ounding environmental factors such as indoor/outdoor\, bright/dark\, backg rounds\, and light strength. We have conducted extensive experiments to ev aluate the performance of our method using various input parameters and ad vanced Deep Neural Network (DNN) architectures on multiple public DeepFake datasets. The empirical results show that our technique achieves high acc uracy (99.0%) in detecting sophisticated deepfake images.\n\nShort Bio:\n\ nDr. Baek-Young Choi is a Professor at the University of Missouri – Kans as City (UMKC). She received her Ph.D. degree in Computer Science and Engi neering from the University of Minnesota\, Twin Cities. She published thre e books on network monitoring\, storage systems\, and cloud computing. She has been a faculty fellow of the National Aeronautics and Space Administr ation (NASA)\, U.S. Air Force Research Laboratory’s Visiting Faculty Res earch Program (AFRL-VFRP) and Korea Telecom’s - Advance Institute of Tec hnology (KT-AIT). She is an associate editor for IEEE Consumer Electronics Magazine and was an associate editor for IEEE Internet-of-Things Journal\ , Springer Journal of Telecommunication Systems\, Elsevier Journal Compute r Networks. Her research interests generally lie in the broad area of netw orking and communications\, with specific emphasis on Internet-of-Things\, cybersecurity\, and smart city technologies. She is a senior member of AC M and IEEE\, and a chair of IEEE Women in Communications Engineering (WICE ).\n\nBaek-Young Choi\, Ph.D. Professor of Computer Science School of Scie nce and Engineering University of Missouri-Kansas City\n\nSpeaker(s): Prof essor Dr Baek-Young Choi\, \n\nAgenda: \n7pm Meet and Greet the Visiting P rofessor Dr Baek-Young Choi.\n\nPresentation.\n\nIntroduction to Women In Communications Engineering / WICE & WIE Connections.\n\nSay hello to colle agues.\n\nSummary and conclusions.\n\nVirtual: https://events.vtools.ieee. org/m/347211 LOCATION:Virtual: https://events.vtools.ieee.org/m/347211 ORGANIZER:kit.august@gmail.com SEQUENCE:6 SUMMARY:Professor Dr Baek-Young Choi: The Eyes Have It - liveness detection of mobile authentication & deepfake detection URL;VALUE=URI:https://events.vtools.ieee.org/m/347211 X-ALT-DESC:Description: <br /><p>IEEE NJ Coast PACE SIGHT Group\, together with Computer Chapter and cosponsors present</p>\n<p>Professor Dr Baek-You ng Choi.</p>\n<p><strong>Title</strong>:&nbsp\;The Eyes Have It</p>\n<p><s trong>Abstract</strong>: In this talk\, we will discuss how eyes can be us ed for liveness detection of mobile authentication and deepfake detection. &nbsp\;</p>\n<p>As the need for contactless biometric authentication becom es more significant during COVID-19 and beyond\, the popular biometric aut hentication method for mobile devices\, iris detection\, and facial recogn ition confronts various usability\, security\, and privacy concerns\, incl uding mask-wearing and various Presentation Attacks (PA). Specifically\, l iveness detection against spoofed artifacts is one of the most challenging tasks as many existing methods cannot conclusively assess the user's phys ical presence in unsupervised environments. Even though several methods ha ve been proposed for tackling PA with motion challenges and 3D mapping\, m ost require expensive depth sensors and fail to detect sophisticated 3D re construction attacks. We present a software-based face PA Detection (PAD) method named\, which creates challenges and detects meaningful corneal spe cular reflection responses from human eyes. To detect human liveness\, our system generates multiple screen image patterns as a challenge\, then cap tures the response of corneal specular reflections using a frontal camera and analyzes the images using lightweight Machine Learning (ML) techniques . Liveness detection system components include challenge pattern generatio n\, reflection image augmentation (e.g.\, super-resolution)\, and ML-based analyses. We have implemented the system as Android\, iOS\, and web apps. Our extensive experimental results show that our scheme achieves liveness detection with high accuracy at around 200 ms against various types of so phisticated PAs. The liveness detection can be applied for multiple contac tless biometric authentications accurately and efficiently without any cos tly extra sensors nor involving users' active responses.</p>\n<p>The secon d part is about deepfake detection through eyes and environment.&nbsp\;Dee pfake techniques presenting AI-generated fictitious&nbsp\;facial images of people can negatively influence the authenticity of online information. S tarting as benign mesmerizing memes\, they can be used malignantly to orig inate&nbsp\;deception\, manipulation\, persecution\, and seduction\, defyi ng societal quality and human rights. However\, due to&nbsp\;the recent de velopment of sophisticated deepfake generation technologies\, it is gettin g harder to distinguish counterfeit images. Thus\, instead of relying on&n bsp\;a single aspect of the visual features\, we detect various features f rom the specular reflection images such as color components\, shapes\, and textures to check the coordination with the surrounding environmental fac tors such as indoor/outdoor\, bright/dark\, backgrounds\, and light streng th.&nbsp\;We have conducted extensive experiments to evaluate the&nbsp\;pe rformance of our method using various input parameters&nbsp\;and advanced Deep Neural Network (DNN) architectures&nbsp\;on multiple public DeepFake datasets. The empirical results show that our technique achieves high accu racy (99.0%)&nbsp\;in detecting sophisticated deepfake images.</p>\n<p><st rong>Short Bio:</strong></p>\n<p>Dr. Baek-Young Choi is a Professor at the University of Missouri &ndash\; Kansas City (UMKC). She received her Ph.D . degree in Computer Science and Engineering from the University of Minnes ota\, Twin Cities. She published three books on network monitoring\, stora ge systems\, and cloud computing. She has been a faculty fellow of the Nat ional Aeronautics and Space Administration (NASA)\, U.S. Air Force Researc h Laboratory&rsquo\;s Visiting Faculty Research Program (AFRL-VFRP) and Ko rea Telecom&rsquo\;s - Advance Institute of Technology (KT-AIT). She is an associate editor for IEEE Consumer Electronics Magazine and was an associ ate editor for IEEE Internet-of-Things Journal\, Springer Journal of Telec ommunication Systems\, Elsevier Journal Computer Networks. Her research in terests generally lie in the broad area of networking and communications\, with specific emphasis on Internet-of-Things\, cybersecurity\, and smart city technologies. She is a senior member of ACM and IEEE\, and a chair of IEEE Women in Communications Engineering (WICE).</p>\n<p><strong>Baek-You ng Choi\,&nbsp\;<em>Ph.D. </em></strong>Professor of Computer Science Scho ol of Science and Engineering University of Missouri-Kansas City</p><br /> <br />Agenda: <br /><p>7pm Meet and Greet the Visiting Professor Dr Baek-Y oung Choi.</p>\n<p>Presentation.</p>\n<p>Introduction to Women In Communic ations Engineering / WICE &amp\; WIE Connections.</p>\n<p>Say hello to col leagues.</p>\n<p>Summary and conclusions.</p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR