all InfoSec news
PAC-Private Algorithms
May 10, 2024, 3:18 a.m. |
IACR News www.iacr.org
ePrint Report: PAC-Private Algorithms
Mayuri Sridhar, Hanshen Xiao, Srinivas Devadas
Provable privacy typically requires involved analysis and is often associated with unacceptable accuracy loss. While many empirical verification or approximation methods, such as Membership Inference Attacks (MIA) and Differential Privacy Auditing (DPA), have been proposed, these do not offer rigorous privacy guarantees. In this paper, we apply recently-proposed Probably Approximately Correct (PAC) Privacy to give formal, mechanized, simulation-based proofs for a range of practical, black-box algorithms: K-Means, Support Vector Machines …
accuracy algorithms analysis attacks auditing differential privacy eprint report loss offer pac privacy private report verification
More from www.iacr.org / IACR News
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Principal Security Research Engineer (Prisma Cloud)
@ Palo Alto Networks | Bengaluru, India
National Security Solutions Fall 2024 Co-Op - Positioning, Navigation and Timing (PNT) Intern
@ KBR, Inc. | USA, Beavercreek Township, 4027 Colonel Glenn Highway, Suite 300, Ohio
Sr Principal Embedded Security Software Engineer
@ The Aerospace Corporation | HIA32: Cedar Rapids, IA 400 Collins Rd NE , Cedar Rapids, IA, 52498-0505 USA