Journal of Privacy and Confidentiality

10 papers9 directions
The Journal of Privacy and Confidentiality is a research venue active since 2010 that focuses on the intersection of data privacy, statistical confidentiality, and machine learning. It serves as a platform for technical research into formal privacy frameworks, specifically differential privacy. The journal publishes work on the theoretical foundations of privacy, including optimal privacy analysis, mechanism decomposition, and the systematic analysis of privacy definitions. In the context of machine learning and artificial intelligence, the venue is known for its contributions to machine unlearning and the development of privacy-preserving algorithms for generative models. Research published here includes studies on adaptive composition for differential privacy, tight privacy accounting for DP-SGD, and methods for handling adaptive deletion requests. The journal also addresses practical implementation challenges, such as mitigating floating-point side channels in privacy mechanisms and evaluating disclosure avoidance systems in large-scale applications like the 2020 Census. Prolific contributors to the journal include researchers such as Daniel Kifer, Danfeng Zhang, and Clement Louis Canonne. By hosting studies on reconstruction attacks and the refinement of privacy-loss parameters, the venue facilitates the development of standards for deploying AI systems that handle sensitive information. Its scope encompasses both the mathematical proofs of privacy guarantees and the empirical analysis of privacy-preserving systems.

Papers by Year

2025 4
2024 2
2022 3
2010 1

Top Research Directions

Research directions most represented by papers from this venue.

Statistical Privacy over Continuous Domains 1
The Privacy Accounting Gap in Stochastic Gradient Descent 1
Floating-Point Vulnerabilities in Differential Privacy 1
Dynamic Privacy Budget Allocation for Machine Learning 1
Tracking Privacy Loss Distributions in Differential Privacy 1
Private Hyperparameter Optimization 1
Machine Unlearning for Regulatory Data Deletion Requirements 1
Privacy Preserving Computation via Homomorphic Encryption 1
Learning from Privacy Constrained Distributed Data Silos 1

Top Authors

AuthorPapers
Daniel Kifer6
Clement Louis Canonne1
Yingtai Xiao1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Avoiding Floating-Point Side Channels in the Report Noisy Max with Gap Mechanism2025
Bridging the Privacy Accounting Gap in DP-SGD2025
Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters2025
Tight Bounds for Machine Unlearning via Differential Privacy2025
Geographic Spines in the 2020 Census Disclosure Avoidance System2024
Reconstruction Attacks on Aggressive Relaxations of Differential Privacy2024
An Axiomatic View of Statistical Privacy and Utility2022
Introduction to Special Section2022
Towards a Systematic Analysis of Privacy Definitions2022
Privacy-preserving Maximum Likelihood Estimation for Distributed Data2010