BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Jerusalem
BEGIN:DAYLIGHT
DTSTART:20250328T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=-1FR;BYMONTH=3
TZNAME:IDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T010000
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250308T173828Z
UID:AAC398CC-0F59-4747-A96F-5D263657E362
DTSTART;TZID=Asia/Jerusalem:20250129T113000
DTEND;TZID=Asia/Jerusalem:20250129T123000
DESCRIPTION:Securing Modern Systems is More Challenging Than Ever (and Requ
 ires New and Dedicated Guardrails).\n\nAbstract. Over the past decade\, an
  increasing number of systems and devices have gained Internet connectivit
 y and been enhanced with sensing capabilities and AI. While these advancem
 ents have created a world of smarter\, more automated\, and highly connect
 ed devices\, they have also introduced significant security and privacy ch
 allenges that cannot be effectively addressed with traditional countermeas
 ures.\n\nIn the first part of this talk\, we will explore the security and
  privacy concerns of cyber-physical systems. Specifically\, we will examin
 e new threats that have emerged with the deployment of technologies like d
 rones and Teslas in real-world environments. Our discussion will highlight
  methods for detecting intrusive drone filming and securing Teslas against
  time-domain adversarial attacks.\n\nThe second part of the talk focuses o
 n the challenges posed by the coexistence of functional devices with limit
 ed computational power (that do not adhere to Moore’s law) alongside sen
 sors with ever-increasing sampling rates. We will explore how threats such
  as cryptanalysis and speech eavesdropping—previously accessible only to
  well-resourced adversaries—can now be executed by ordinary attackers us
 ing readily available hardware like photodiodes and video cameras. These a
 ttacks leverage optical traces or video footage from a device’s power LE
 D to extract sensitive information.\n\nFinally\, in the last part of the t
 alk\, we will address the emerging need to secure GenAI-powered applicatio
 ns against a new category of threats we call Promptware. This threat highl
 ights the evolving landscape of vulnerabilities introduced by generative A
 I systems.\n\nSpeaker(s): Dr. Ben Nassi\n\nRoom: #506\, Bldg: Zisapel Buil
 ding\, Technion City\, Haifa\, Haifa District\, Israel
LOCATION:Room: #506\, Bldg: Zisapel Building\, Technion City\, Haifa\, Haif
 a District\, Israel
ORGANIZER:yaron.b.hay@gmail.com
SEQUENCE:13
SUMMARY:ceClub Seminar - Securing Modern Systems is More Challenging Than E
 ver (and Requires New and Dedicated Guardrails)
URL;VALUE=URI:https://events.vtools.ieee.org/m/463759
X-ALT-DESC:Description: <br /><div><strong>Securing Modern Systems is More 
 Challenging Than Ever (and Requires New and Dedicated Guardrails).</strong
 ></div>\n<div class="elementToProof">&nbsp\;</div>\n<div>Abstract. Over th
 e past decade\, an increasing number of systems and devices have gained In
 ternet connectivity and been enhanced with sensing capabilities and AI. Wh
 ile these advancements have created a world of smarter\, more automated\, 
 and highly connected devices\, they have also introduced significant secur
 ity and privacy challenges that cannot be effectively addressed with tradi
 tional countermeasures.</div>\n<div><br>In the first part of this talk\, w
 e will explore the security and privacy concerns of cyber-physical systems
 . Specifically\, we will examine new threats that have emerged with the de
 ployment of technologies like drones and Teslas in real-world environments
 . Our discussion will highlight methods for detecting intrusive drone film
 ing and securing Teslas against time-domain adversarial attacks.<br><br>Th
 e second part of the talk focuses on the challenges posed by the coexisten
 ce of functional devices with limited computational power (that do not adh
 ere to Moore&rsquo\;s law) alongside sensors with ever-increasing sampling
  rates. We will explore how threats such as cryptanalysis and speech eaves
 dropping&mdash\;previously accessible only to well-resourced adversaries&m
 dash\;can now be executed by ordinary attackers using readily available ha
 rdware like photodiodes and video cameras. These attacks leverage optical 
 traces or video footage from a device&rsquo\;s power LED to extract sensit
 ive information.<br><br>Finally\, in the last part of the talk\, we will a
 ddress the emerging need to secure GenAI-powered applications against a ne
 w category of threats we call Promptware. This threat highlights the evolv
 ing landscape of vulnerabilities introduced by generative AI systems.</div
 >
END:VEVENT
END:VCALENDAR