Publishing Naive Bayesian Classifiers: Privacy without Accuracy Loss

Summary: Publishes privacy-safe Naive Bayes statistics/views without changing classifier decisions or accuracy, avoiding randomization/anonymization loss. A linear-time ratio-perturbation algorithm yields publishable rational/synthetic datasets, with extensions beyond uniform priors. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 10164
Venue: VLDB
Year: 2009
Pagerank: 5.093636e-05
Overall Rank: 12,545 | 13.93%
DOI: 10.14778/1687627.1687759

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Barzan Mozafari (University of California Los Angeles)
2. Carlo Zaniolo (University of California Los Angeles)

BibTeX Citation

@article{mozafari_vldb09,
        title = {{Publishing Naive Bayesian Classifiers: Privacy without Accuracy Loss}},
        author = {Mozafari, Barzan and Zaniolo, Carlo},
        journal = {PVLDB},
        series = {{VLDB} '09},
        doi = {10.14778/1687627.1687759},
        url = {https://doi.org/10.14778/1687627.1687759},
        year = {2009}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
70	Privacy-Preserving Data Mining	2000	SIGMOD	0.0003804755
218	Limiting Privacy Breaches in Privacy Preserving Data Mining	2003	PODS	0.00024420564
384	On the Complexity of Optimal K-Anonymity	2004	PODS	0.00019510305
450	Incognito: Efficient Full-Domain K-Anonymity	2005	SIGMOD	0.00018155142
1,088	A Formal Analysis of Information Disclosure in Data Exchange	2004	SIGMOD	0.00012248135
1,746	The Boundary Between Privacy and Utility in Data Publishing	2007	VLDB	9.8564338e-05
2,017	Auditing Boolean Attributes	2000	PODS	9.3006188e-05
2,401	Simulatable Auditing	2005	PODS	8.6299652e-05
3,845	Checking for k-Anonymity Violation by Views	2005	VLDB	7.0779843e-05
4,559	Deriving Private Information from Randomized Data	2005	SIGMOD	6.6318893e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	775	Differentially Private Data Cubes: Optimizing Noise Sources and Consistency	2011	SIGMOD
2	9,135	Universally Optimal Privacy Mechanisms for Minimax Agents	2010	PODS
3	70	Privacy-Preserving Data Mining	2000	SIGMOD
4	7,841	Quantifying identifiability to choose and audit epsilon in differentially private deep learning	2021	VLDB
5	3,974	Epistemic Privacy	2008	PODS
6	12,809	Privacy in Data Systems	2003	PODS
7	2,856	Publishing Set-Valued Data via Differential Privacy	2011	VLDB
8	1,746	The Boundary Between Privacy and Utility in Data Publishing	2007	VLDB
9	6,701	Information Preservation in Statistical Privacy and Bayesian Estimation of Unattributed Histograms	2013	SIGMOD
10	1,169	PrivBayes: Private Data Release via Bayesian Networks	2014	SIGMOD