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

• URL: http://arxiv.org/abs/2603.12142v1
• Date: Thu, 12 Mar 2026 16:43:55 GMT
• Title: Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing (Extended Version)
• Abstract summary: This paper introduces reconstruction advantage, a unified risk metric that consistently captures risk across membership inference, attribute inference, and data reconstruction.<n>We derive tight bounds that relate DP noise to adversarial advantage and characterize optimal adversarial strategies for arbitrary DP mechanisms and attacker knowledge.<n>We show that reconstruction advantage improves the accuracy and scope of DP auditing and enables more effective utility-privacy trade-offs in DP-enabled data management systems.
• Score: 3.497537146514306
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Differential Privacy (DP) is widely adopted in data management systems to enable data sharing with formal disclosure guarantees. A central systems challenge is understanding how DP noise translates into effective protection against inference attacks, since this directly determines achievable utility. Most existing analyses focus only on membership inference -- capturing only a threat -- or rely on reconstruction robustness (ReRo). However, under realistic assumptions, we show that ReRo can yield misleading risk estimates and violate claimed bounds, limiting their usefulness for principled DP calibration and auditing. This paper introduces reconstruction advantage, a unified risk metric that consistently captures risk across membership inference, attribute inference, and data reconstruction. We derive tight bounds that relate DP noise to adversarial advantage and characterize optimal adversarial strategies for arbitrary DP mechanisms and attacker knowledge. These results enable risk-driven noise calibration and provide a foundation for systematic DP auditing. We show that reconstruction advantage improves the accuracy and scope of DP auditing and enables more effective utility-privacy trade-offs in DP-enabled data management systems.

Related papers

• Masking Radar Cognition under Adversarial Surveillance: A Distributional Privacy Framework [0.9786690381850356]
  We propose a framework to conceal the strategic decision-making processes of a cognitive radar (CR) under adversarial surveillance.<n>We show that both WDPCH-SU and WDPCH-DU satisfy $$-distribution privacy ($$-DistP) against inference-based adversarial attacks.<n>Results are highly promising in many 6G scenarios such as network slicing for automated driving and UAV coordination.
  arXiv  Detail & Related papers  (2026-09-07T12:32:56Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models [35.164227002323706]
  We investigate privacy risks under DP adaptations in large language models (LLMs)<n>We benchmark these risks using state-of-the-art attacks such as robust membership inference and canary data extraction.<n>We find that parameter-efficient fine-tuning methods, such as LoRA, achieve the highest empirical privacy protection for OOD data.
  arXiv  Detail & Related papers  (2026-06-08T12:21:02Z)
• Exploring the Integration of Differential Privacy in Cybersecurity Analytics: Balancing Data Utility and Privacy in Threat Intelligence [0.0]
  This paper considers the implementation of Differential Privacy (DP) in cybersecurity analytics.<n>DP ensures privacy by adding a controlled noise to data outputs and avoids sensitive information disclosure.<n>This paper makes DP one of the key strategies to improve privacy-preserving analytics in the field of cybersecurity.
  arXiv  Detail & Related papers  (2026-01-01T16:31:47Z)
• RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration [81.38705556267917]
  Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations.<n>We introduce a theoretical framework that reconstructs the underlying risk concept space.<n>We propose RADAR, a multi-agent collaborative evaluation framework.
  arXiv  Detail & Related papers  (2025-09-28T09:35:32Z)
• Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries [17.780319275883127]
  Differential Privacy is a family of definitions that bound the worst-case privacy leakage of a mechanism.<n>This work sheds light on what the worst-case guarantee of DP implies about the success of attackers that are more representative of real-world privacy risks.
  arXiv  Detail & Related papers  (2025-07-10T20:36:31Z)
• Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy [24.723577119566112]
  We show that bounds on attack success can take the same unified form across re-identification, attribute inference, and data reconstruction risks.<n>Our results are tighter than prior methods using $varepsilon$-DP, R'enyi DP, and concentrated DP.
  arXiv  Detail & Related papers  (2025-07-09T15:59:30Z)
• Verifiable Exponential Mechanism for Median Estimation [4.083860866484599]
  We propose the first verifiable implementation of the exponential mechanism using zk-SNARKs.<n>As a concrete application, we present the first verifiable differentially private (DP) median estimation scheme.
  arXiv  Detail & Related papers  (2025-05-22T05:31:22Z)
• Enhancing Privacy in Semantic Communication over Wiretap Channels leveraging Differential Privacy [51.028047763426265]
  Semantic communication (SemCom) improves transmission efficiency by focusing on task-relevant information.<n> transmitting semantic-rich data over insecure channels introduces privacy risks.<n>This paper proposes a novel SemCom framework that integrates differential privacy mechanisms to protect sensitive semantic features.
  arXiv  Detail & Related papers  (2025-04-23T08:42:44Z)
• Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems [89.35169042718739]
  collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data to cloud servers.<n>Recent studies have revealed that these intermediate features may not sufficiently preserve privacy, as information can be leaked and raw data can be reconstructed via model inversion attacks (MIAs)<n>This work first theoretically proves that the conditional entropy of inputs given intermediate features provides a guaranteed lower bound on the reconstruction mean square error (MSE) under any MIA.<n>Then, we derive a differentiable and solvable measure for bounding this conditional entropy based on the Gaussian mixture estimation and propose a conditional entropy algorithm to enhance the inversion robustness
  arXiv  Detail & Related papers  (2025-03-01T07:15:21Z)
• Visual Privacy Auditing with Diffusion Models [47.0700328585184]
  We introduce a reconstruction attack based on diffusion models (DMs) that only assumes adversary access to real-world image priors.<n>We find that (1) real-world data priors significantly influence reconstruction success, (2) current reconstruction bounds do not model the risk posed by data priors well, and DMs can serve as auditing tools for visualizing privacy leakage.
  arXiv  Detail & Related papers  (2024-03-12T12:18:55Z)
• From Mean to Extreme: Formal Differential Privacy Bounds on the Success of Real-World Data Reconstruction Attacks [54.25638567385662]
  Differential Privacy in machine learning is often interpreted as guarantees against membership inference.<n> translating DP budgets into quantitative protection against the more damaging threat of data reconstruction remains a challenging open problem.<n>This paper bridges the critical gap by deriving the first formal privacy bounds tailored to the mechanics of demonstrated "from-scratch" attacks.
  arXiv  Detail & Related papers  (2024-02-20T09:52:30Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking [83.48804199140758]
  We propose a learning-to-mis-rank formulation to perturb the ranking of the system output. We also perform a back-box attack by developing a novel multi-stage network architecture. Our method can control the number of malicious pixels by using differentiable multi-shot sampling.
  arXiv  Detail & Related papers  (2020-04-08T18:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.