BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240626T180034Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240626T180000
DTEND;TZID=America/Los_Angeles:20240626T190000
UID:dac_DAC 2024_sess237_RESEARCH1622@linklings.com
SUMMARY:PABTG: A Pipeline Architecture for Beaver Triple Generation in Sec
 ure Multi-party Computation
DESCRIPTION:Work-in-Progress Poster\n\nXiaolin Li, Wei Yan, Hongwei Liu, a
 nd Qinfen Hao (Institute of Computing Technology, Chinese Academy of Scien
 ces)\n\nSecure Multi-Party Computation (MPC) is proposed to protect the da
 ta privacy from a group of parties, enabling collaborative computation of 
 correct results for target functions. SPDZ, a set of mature MPC protocols 
 widely used in machine learning and other scenarios, requires a significan
 t number of Beaver triples for secure multiplications among parties. Given
  no Trusted Third Party (TTP) participated, the generation time constitute
 s over 92% of the total running time. This paper introduces MPC-PAT, a hig
 h-performance pipeline architecture designed for efficient Beaver triple g
 eneration. MPC-PAT accelerates random number generation, hash function, an
 d modular multiplication in two finite fields. The evaluation results from
  its FPGA implementation demonstrate substantial speedups, ranging from 40
 x to 99x for basic operations and 2x to 136x for various convolutional net
 works compared to the existing SPDZ works.\n\nTopic: AI, Autonomous System
 s, Cloud, Design, EDA, Embedded Systems, IP, Security
END:VEVENT
END:VCALENDAR