Privacy Amplification for Episodic Training Methods

Conference · Sun Jan 01 04:00:00 EST 2023

OSTI ID:1923187

Tombs, Vandy ^[1]; Kotevska, Olivera ^[1]; Young, Steven ^[1]

---

1. ORNL

It has been shown that differential privacy bounds improve when subsampling within a randomized mechanism. Episodic training, utilized in many standard machine learning techniques, uses a multistage subsampling procedure which has not been previously analyzed for privacy bound amplification. In this paper, we focus on improving the calculation of privacy bounds in episodic training by thoroughly analyzing privacy amplification due to subsampling with a multi-stage subsampling procedure. The newly developed bound can be incorporated into existing privacy accounting methods.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1923187
• Country of Publication: United States
• Language: English