BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Asia/Calcutta BEGIN:STANDARD DTSTART:19451014T230000 TZOFFSETFROM:+0630 TZOFFSETTO:+0530 TZNAME:IST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210321T094329Z UID:7AA96A16-803F-404E-8390-7149843DEAC5 DTSTART;TZID=Asia/Calcutta:20210315T110000 DTEND;TZID=Asia/Calcutta:20210315T120000 DESCRIPTION:IEEE Computational Intelligence Society Chapter - IEEE Gujarat Section and Ahmedabad University invites you to following expert talk\n\nT itle: Adversarial Examples of Deep Learning System and Its Defense\nSpeake r: Minoru Kuribayashi\, Okayama University\, Japan\nMode: Virtual\nDate: 1 5.03.2021\nTime:1100 am to 12.00 pm\nRegistration form: https://docs.googl e.com/forms/d/1SGqmPdU_2pK33tVmaBNcLwCnUcj1uZA2WXVz1MfXsDc/edit?usp=sharin g.\n\nAbstract: Deep neural network (DNN) is known to be vulnerable to adv ersarial attacks\, where adversarial noise is added to images or speech fi les so that a target DNN-based system outputs wrong results. Adversarial e xamples are the content which fools a system. Examples of systems that can be attacked using adversarial examples include face recognition and autom atic driving system. Moreover\, the DNN training data set could also be po isoned in the situation where the adversary has access to the training dat abase. One of the defense techniques is to detect such adversarial images by observing the outputs of a DNN-based system when noise removal filters are operated. Such operation-oriented characteristics enable us to classif y a given image whether it is normal or adversarial. In this talk\, I will show state-of-the-art techniques for detecting adversarial examples.\n\nA bout Speaker:\nMinoru Kuribayashi received B.E.\, M.E.\, and D.E degrees f rom Kobe University\, Japan\, in 1999\, 2001\, and 2004. He was a Research Associate and an Assistant Professor at Kobe University from 2002 to 2007 and from 2007 to 2015\, respectively. Since 2015\, he has been an Associa te Professor in the Graduate School of Natural Science and Technology\, Ok ayama University. His research interests include multimedia security\, dig ital watermarking\, cryptography\, and coding theory. He serves as an asso ciate editor of JISA and IEICE. He is a vice chair of APSIPA TC of Multime dia Security and Forensics\, and a TC member of IEEE SPS Information Foren sics and Security. He received the Young Professionals Award from IEEE Kan sai Section in 2014\, and the Best Paper Award from IWDW 2015 and 2019. He is a senior member of IEEE and IEICE.\n\nSpeaker(s): Dr. Minoru Kuribayas hi\, \n\nAhmedabad\, Gujarat\, India\, Virtual: https://events.vtools.ieee .org/m/264789 LOCATION:Ahmedabad\, Gujarat\, India\, Virtual: https://events.vtools.ieee. org/m/264789 ORGANIZER:mehul.raval@ahduni.edu.in SEQUENCE:1 SUMMARY:Expert Talk URL;VALUE=URI:https://events.vtools.ieee.org/m/264789 X-ALT-DESC:Description: <br /><div>\n<div>\n<div>IEEE Computational Intelli gence Society Chapter - IEEE Gujarat Section and Ahmedabad University invi tes you to following&nbsp\;expert talk</div>\n<div>&nbsp\;</div>\n</div>\n <div>Title: Adversarial Examples of Deep Learning System and Its Defense</ div>\n<div>Speaker:&nbsp\; Minoru Kuribayashi\,&nbsp\;&nbsp\;Okayama Unive rsity\, Japan</div>\n<div>Mode: Virtual</div>\n</div>\n<div>Date: 15.03.20 21</div>\n<div>Time:1100 am to 12.00 pm&nbsp\;</div>\n<div>Registration fo rm:&nbsp\;<a href="https://docs.google.com/forms/d/1SGqmPdU_2pK33tVmaBNcLw CnUcj1uZA2WXVz1MfXsDc/edit?usp=sharing" target="_blank" rel="noopener" dat a-saferedirecturl="https://www.google.com/url?q=https://docs.google.com/fo rms/d/1SGqmPdU_2pK33tVmaBNcLwCnUcj1uZA2WXVz1MfXsDc/edit?usp%3Dsharing&amp\ ;source=gmail&amp\;ust=1615007629006000&amp\;usg=AFQjCNFjLms_ccHAamd6z1s9r 4-QjPyyjQ">https://docs.google.com/<wbr />forms/d/1SGqmPdU_<wbr />2pK33tVm aBNcLwCnUcj1uZA2WXVz1M<wbr />fXsDc/edit?usp=sharing</a>.&nbsp\;</div>\n<di v>&nbsp\;</div>\n<div>Abstract:&nbsp\; Deep neural network (DNN) is known to be vulnerable to adversarial attacks\, where adversarial noise is added to images or speech files so that a target DNN-based system outputs wrong results. Adversarial examples are the content which fools a system. Examp les of systems that can be attacked using adversarial examples include fac e recognition and automatic driving system. Moreover\, the DNN training da ta set could also be poisoned in the situation where the adversary has acc ess to the training database. One of the defense techniques is to detect s uch adversarial images by observing the outputs of a DNN-based system when noise removal filters are operated. Such operation-oriented characteristi cs enable us to classify a given image whether it is normal or adversarial . In this talk\, I will show state-of-the-art techniques for detecting adv ersarial examples.&nbsp\;</div>\n<div>&nbsp\;</div>\n<div>About Speaker:</ div>\n<div>&nbsp\;Minoru Kuribayashi received B.E.\, M.E.\, and D.E degree s from Kobe University\, Japan\, in 1999\, 2001\, and 2004. He was a Resea rch Associate and an Assistant Professor at Kobe University from 2002 to 2 007 and from 2007 to 2015\, respectively. Since 2015\, he has been an Asso ciate Professor in the Graduate School of Natural Science and Technology\, Okayama University. His research interests include multimedia security\, digital watermarking\, cryptography\, and coding theory. He serves as an a ssociate editor of JISA and IEICE. He is a vice chair of APSIPA TC of Mult imedia Security and Forensics\, and a TC member of IEEE SPS Information Fo rensics and Security. He received the Young Professionals Award from IEEE Kansai Section in 2014\, and the Best Paper Award from IWDW 2015 and 2019. He is a senior member of IEEE and IEICE.</div> END:VEVENT END:VCALENDAR