BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG D 1.2
DTSTART;TZID=Europe/Stockholm:20240603T153000
DTEND;TZID=Europe/Stockholm:20240603T160000
UID:submissions.pasc-conference.org_PASC24_sess125_msa312@linklings.com
SUMMARY:Cryptographic Protection of Random Access Memory for High Performa
 nce Confidential Computing
DESCRIPTION:Minisymposium\n\nRoberto Avanzi (University of Haifa)\n\nConfi
 dential Computing safeguards data in use against unauthorized access or mo
 dification, including by privileged software. Architectures like Intel SGX
 , AMD SEV, Arm CCA, and IBM Ultravisor implement this protection through a
 ccess control policies. In some cases, they also employ cryptographic memo
 ry protection schemes, which are the subject of this talk. We review such 
 schemes from academia and industry and categorize them based on protection
  levels corresponding to Adversaries with varying capabilities, budgets, a
 nd strategies. The cryptographic memory protection schemes are built from 
 encryption and integrity primitives, modes of operation, and anti-replay s
 tructures. We consider the choices of these building blocks and of their c
 ombinations. The performance impact of selected designs is assessed throug
 h the SimPoints methodology in a simulated system. We focus on technologie
 s that maintain good software speeds and do not rely on components which a
 re external to the System-on-a-Chip (SoC). Therefore, methods such as Obli
 vious RAMs or the protection of the SoC-to-memory link are excluded. Final
 ly, we introduce novel solutions to minimize performance and memory overhe
 ads: Our integrity trees based on 3-way split counters outperform the stat
 e-of-the-art while being more straightforward to implement. Their compactn
 ess allows storage in on-chip physically protected memory.\n\nDomain: Comp
 utational Methods and Applied Mathematics\n\nSession Chairs: Timothy Dykes
  (HPE) and Tiziano Müller (HPE)
END:VEVENT
END:VCALENDAR
