Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)

Export BriefConnect with Author
View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $9K - $13K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (61)

[1]
On Estimating the Strength of Differentially Private Mechanisms in a Black-Box Setting
2025Daniele Gorla, Louis Jalouzot et al.
[2]
Synthetic Tabular Data: Methods, Attacks and Defenses
2025G. Cormode, Samuel Maddock et al.
[3]
Auditing f-Differential Privacy in One Run
2024Saeed Mahloujifar, Luca Melis et al.
[4]
Attack-Aware Noise Calibration for Differential Privacy
2024Bogdan Kulynych, J. Gómez et al.
[5]
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
2024Meenatchi Sundaram Muthu Selva Annamalai, Emiliano De Cristofaro
[6]
Eureka: A General Framework for Black-box Differential Privacy Estimators
2024Yun Lu, Yu Wei et al.
[7]
Analysis and Measurement of Attack Resilience of Differential Privacy
2023Patricia Guerra-Balboa, Annika Sauer et al.
[8]
Total Variation Meets Differential Privacy
2023Elena Ghazi, Ibrahim Issa
[9]
Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective
2023Héber H. Arcolezi, S'ebastien Gambs
[10]
Privacy Auditing with One (1) Training Run
2023T. Steinke, Milad Nasr et al.
[11]
Measuring Re-identification Risk
2023Cj Carey, Travis Dick et al.
[12]
What Are the Chances? Explaining the Epsilon Parameter in Differential Privacy
2023Priyanka Nanayakkara, Mary Anne Smart et al.
[13]
Bounding Training Data Reconstruction in DP-SGD
2023Jamie Hayes, Saeed Mahloujifar et al.
[14]
TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
2022F. Houssiau, James Jordon et al.
[15]
Bayesian and Frequentist Semantics for Common Variations of Differential Privacy: Applications to the 2020 Census
2022Daniel Kifer, John M. Abowd et al.
[16]
On the Risks of Collecting Multidimensional Data Under Local Differential Privacy
2022Héber H. Arcolezi, S. Gambs et al.
[17]
Are Attribute Inference Attacks Just Imputation?
2022Bargav Jayaraman, David Evans
[18]
Debugging Differential Privacy: A Case Study for Privacy Auditing
2022Florian Tramèr, A. Terzis et al.
[19]
Reconstructing Training Data with Informed Adversaries
2022Borja Balle, Giovanni Cherubin et al.
[20]
An Adversarial Approach to Protocol Analysis and Selection in Local Differential Privacy
2022M. E. Gursoy, Ling Liu et al.

Showing 20 of 61 references

Founder's Pitch

"A novel risk metric for enhancing differential privacy calibration and auditing."

Differential PrivacyScore: 4View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

1/4 signals

2.5

Quick Build

0/4 signals

0

Series A Potential

0/4 signals

0

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/12/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.

Related Papers

Loading…