Journal of Privacy and Confidentiality 2025

4 papers
The 2025 edition of the Journal of Privacy and Confidentiality focuses on machine unlearning and the refinement of privacy accounting frameworks. Research themes include continual unlearning for large language and generative models, as well as handling adaptive deletion requests. Several papers address the theoretical aspects of differential privacy, such as optimal privacy analysis via mechanism decomposition and bridging the accounting gap in Differentially Private Stochastic Gradient Descent (DP-SGD). Technical contributions from this year explore concurrent composition for interactive differential privacy with adaptive parameters and methods to avoid floating-point side channels in the Report Noisy Max with Gap mechanism. Authors contributing to these developments include Clement Louis Canonne, Salil Vadhan, Badih Ghazi, and Samuel Haney. The collected work emphasizes tight privacy bounds and adaptive composition, offering methods to improve the precision and security of privacy-preserving algorithms in dynamic data environments.

Top Research Directions

The 7 research directions with Journal of Privacy and Confidentiality 2025 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Dynamic Privacy Budget Allocation for Machine Learning125.0%
2Floating-Point Vulnerabilities in Differential Privacy125.0%
3Machine Unlearning for Regulatory Data Deletion Requirements125.0%
4Private Hyperparameter Optimization125.0%
5Statistical Privacy over Continuous Domains125.0%
6The Privacy Accounting Gap in Stochastic Gradient Descent125.0%
7Tracking Privacy Loss Distributions in Differential Privacy125.0%

Download all directions as CSV

Institutions

Institutions credited by Journal of Privacy and Confidentiality 2025 papers: a paper credits every institution named in its affiliations, once. 5 institutions share 4 credited papers.

#InstitutionPapersShare20242024 rank
1Binghamton University 125.0%0—
2Google (United States) 125.0%0—
3Harvard University 125.0%0—
4The University of Sydney 125.0%0—
5UNSW Sydney 125.0%0—

Download all institutions as CSV

About this data

Papers. Journal of Privacy and Confidentiality 2025 lists 4 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 4 of 4 papers (100.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of Privacy and Confidentiality 2025”, https://lacuna.tiptreesystems.com/venue/journal-of-privacy-and-confidentiality/2025.

Top Authors

AuthorPapers
Clement Louis Canonne1
Daniel Kifer1
Yingtai Xiao1

Impactful Papers

Papers from Journal of Privacy and Confidentiality 2025 that shaped research clusters.

Influential

Papers

Title
Avoiding Floating-Point Side Channels in the Report Noisy Max with Gap Mechanism
Bridging the Privacy Accounting Gap in DP-SGD
Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
Tight Bounds for Machine Unlearning via Differential Privacy