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:3001\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240626T104500
DTEND;TZID=America/Los_Angeles:20240626T110000
UID:dac_DAC 2024_sess102_RESEARCH941@linklings.com
SUMMARY:Order-Preserving Cryptography for the Confidential Inference in Ra
 ndom Forests: FPGA Design and Implementation
DESCRIPTION:Research Manuscript\n\nRupesh Karn (New York University), Kash
 if Nawaz (Technology Innovation Institute), and Ibrahim (Abe) Elfadel (Kha
 lifa University)\n\nPrior work has addressed the problem of confidential i
 nference in decision trees. Both traditional order-preserving cryptography
  and order-preserving NTRU cryptography have been used to ensure data and 
 model privacy in decision trees. Furthermore, FPGA architectures and imple
 mentations have been proposed for implementing such confidential inference
  algorithms on limited resource, edge platforms such as low-cost FPGA boar
 ds. In this paper, we address the challenging problem of scalability of or
 der-preserving confidential inference to random forests, which are ensembl
 es of decision trees that are meant to improve their classification accura
 cy and reduce their overfitting. The paper develops a methodology and an F
 PGA implementation strategy for scaling up order-preserving cryptography t
 o random forests. In particular, a framework is used to study the multifac
 eted tradeoffs that exist between the number of trees in the random forest
 , the strength of the encryption,  the accuracy of the inferences, and the
  resources of the edge platform. Extensive experiments are conducted using
  the MNIST dataset and the Intel DE10 Standard FPGA board.\n\nTopic: AI\n\
 nKeyword: AI/ML Algorithms\n\nSession Chairs: Parivesh Choudhary (Synopsys
 ) and Anca Molnos (CEA-List)
END:VEVENT
END:VCALENDAR