BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20211210T164218Z UID:7CA536B4-D023-4B2B-A87F-D87E134DE481 DTSTART;TZID=US/Eastern:20211207T120000 DTEND;TZID=US/Eastern:20211207T124500 DESCRIPTION:Machine learning has proven to be helpful in many areas in cybe r security\, e.g.\, malware detection\, intrusion detection\, and fuzzing. The ability of machine learning models to identify patterns allows it to be a valuable tool that can be used to increase efficiency and efficacy wh ile also decreasing costs. This becomes especially important as malicious actors continue to develop more sophisticated attacks against a growing at tack surface. However\, more research must be done before machine learning can be safely integrated into cyber defense as machine learning models th emselves are not secure. In this talk\, I will be presenting an attack aga inst malware detectors using adversarial machine learning and a defense ag ainst such adversaries.\n\nSpeaker(s): Daniel Park\, \n\nVirtual: https:// events.vtools.ieee.org/m/292502 LOCATION:Virtual: https://events.vtools.ieee.org/m/292502 ORGANIZER:lee.seversky.us@ieee.org SEQUENCE:1 SUMMARY:Malware Meets Machine Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/292502 X-ALT-DESC:Description: <br /><p>Machine learning has proven to be helpful in many areas in cyber security\, e.g.\, malware detection\, intrusion det ection\, and fuzzing. The ability of machine learning models to identify p atterns allows it to be a valuable tool that can be used to increase effic iency and efficacy while also decreasing costs. This becomes especially im portant as malicious actors continue to develop more sophisticated attacks against a growing attack surface. However\, more research must be done be fore machine learning can be safely integrated into cyber defense as machi ne learning models themselves are not secure. In this talk\, I will be pre senting an attack against malware detectors using adversarial machine lear ning and a defense against such adversaries.&nbsp\;</p> END:VEVENT END:VCALENDAR