BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20201101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210219T050350Z UID:B3F222B0-2162-4F6D-91A4-1F6400637DBE DTSTART;TZID=America/New_York:20210218T190000 DTEND;TZID=America/New_York:20210218T203000 DESCRIPTION:Machine Learning appears to have made impressive progress on ma ny tasks including image classification\, machine translation\, autonomous vehicle control\, playing complex games including chess\, Go\, and Atari video games\, and more. This has led to much breathless popular press cove rage of Artificial Intelligence\, and has elevated deep learning to an alm ost magical status in the eyes of the public. ML\, especially of the deep learning sort\, is not magic\, however. ML has become so popular that its application\, though often poorly understood and partially motivated by hy pe\, is exploding. In my view\, this is not necessarily a good thing. I am concerned with the systematic risk invoked by adopting ML in a haphazard fashion. Our research at the Berryville Institute of Machine Learning (BII ML) is focused on understanding and categorizing security engineering risk s introduced by ML at the design level. Though the idea of addressing secu rity risk in ML is not a new one\, most previous work has focused on eithe r particular attacks against running ML systems (a kind of dynamic analysi s) or on operational security issues surrounding ML. This talk focuses on two threads: building a taxonomy of known attacks on ML and the results of an architectural risk analysis (sometimes called a threat model) of ML sy stems in general. A list of the top five (of 78 known) ML security risks w ill be presented.\n\nCo-sponsored by: Northern VA/Washington Joint Section Computational Intelligence Society Chapter\n\nSpeaker(s): Gary McGraw\, P h.D.\, \n\nAgenda: \n7:00 pm - Opening Comments and Introduction\n\n7:10 p m - Presentation\n\n8:10 pm - Extended Questions\n\n8:30 pm - Close\n\nVir tual: https://events.vtools.ieee.org/m/258562 LOCATION:Virtual: https://events.vtools.ieee.org/m/258562 ORGANIZER:schulman@computer.org SEQUENCE:9 SUMMARY:Security Engineering for Machine Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/258562 X-ALT-DESC:Description: <br /><p><span style="caret-color: #000000\; color: #000000\; font-family: Helvetica\; font-size: 14px\; font-style: normal\; font-variant-caps: normal\; font-weight: normal\; letter-spacing: normal\ ; orphans: auto\; text-align: start\; text-indent: 0px\; text-transform: n one\; white-space: normal\; widows: auto\; word-spacing: 0px\; -webkit-tex t-size-adjust: auto\; -webkit-text-stroke-width: 0px\; text-decoration: no ne\; display: inline !important\; float: none\;">Machine Learning appears to have made impressive progress on many tasks including image classificat ion\, machine translation\, autonomous vehicle control\, playing complex g ames including chess\, Go\, and Atari video games\, and more. This has led to much breathless popular press coverage of Artificial Intelligence\, an d has elevated deep learning to an almost magical status in the eyes of th e public. ML\, especially of the deep learning sort\, is not magic\, howev er. &nbsp\;ML has become so popular that its application\, though often po orly understood and partially motivated by hype\, is exploding. In my view \, this is not necessarily a good thing. I am concerned with the systemati c risk invoked by adopting ML in a haphazard fashion. Our research at the Berryville Institute of Machine Learning (BIIML) is focused on understandi ng and categorizing security engineering risks introduced by ML at the des ign level. &nbsp\;Though the idea of addressing security risk in ML is not a new one\, most previous work has focused on either particular attacks a gainst running ML systems (a kind of dynamic analysis) or on operational s ecurity issues surrounding ML. This talk focuses on two threads: building a taxonomy of known attacks on ML and the results of an architectural risk analysis (sometimes called a threat model) of ML systems in general. &nbs p\;A list of the top five (of 78 known) ML security risks will be presente d. &nbsp\;</span></p><br /><br />Agenda: <br /><p>7:00 pm - Opening Commen ts and Introduction</p>\n<p>7:10 pm - Presentation</p>\n<p>8:10 pm - Exten ded Questions</p>\n<p>8:30 pm - Close</p> END:VEVENT END:VCALENDAR