all AI news
Privacy Amplification for the Gaussian Mechanism via Bounded Support
March 12, 2024, 4:42 a.m. | Shengyuan Hu, Saeed Mahloujifar, Virginia Smith, Kamalika Chaudhuri, Chuan Guo
cs.LG updates on arXiv.org arxiv.org
Abstract: Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be desirable compared to vanilla DP in real world settings as they tightly upper-bound the privacy leakage for a $\textit{specific}$ individual in an $\textit{actual}$ dataset, rather than considering worst-case datasets. While these frameworks are beginning to gain popularity, to date, there is a lack of private …
abstract accounting arxiv cs.cr cs.lg data dataset differential differential privacy fine-grained fisher frameworks information instance loss per privacy support training type via world
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US