paper-with-me

홈 › Papers

Theoretical Guarantees for Model Auditing with Finite Adversaries

2019-11-08 · Mario Diaz, Peter Kairouz, Jiachun Liao, Lalitha Sankar

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak sensitive features. To identify such privacy violations, existing model auditing techniques use finite adversaries defined as machine learning models with (a) access to some finite side information (e.g., a small auditing dataset), and (b) finite capacity (e.g., a fixed neural network architecture). Our work investigates the requirements under which an unsuccessful attempt to identify privacy violations by a finite adversary implies that no stronger adversary can succeed at such a task. We do so via parameters that quantify the capabilities of the finite adversary, including the size of the neural network employed by such an adversary and the amount of side information it has access to as well as the regularity of the (perhaps privacy-guaranteeing) audited model.

📄 PDF Abstract BibTeX arXiv:1911.03405

Code (0)

등록된 구현이 없습니다.

Tasks

modelPrivacy Preserving

Similar Papers 제목 키워드 기반

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

2024-05-23 · Tudor Cebere, Aurélien Bellet, Nicolas Papernot

Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model,…

Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning

2026-05-21 · Benjamin D. Kim, Lav R. Varshney, Daniel Alabi arxiv

We study black-box auditing for machine learning algorithms that claim R \ 'enyi differential privacy (RDP) guarantees. We introduce an auditing framework, based on hypothesis testing, that directly estimates Rényi diver…

Observational Auditing of Label Privacy

2025-11-18 · Iden Kalemaj, Luca Melis, Maxime Boucher, Ilya Mironov 외 arxiv

Differential privacy (DP) auditing is essential for evaluating privacy guarantees in machine learning systems. Existing auditing methods, however, pose a significant challenge for large-scale systems since they require m…

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios

2024-12-02 · Sangyeon Yoon, Wonje Jeung, Albert No

Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly looser than theoretical privacy guarantees…

Gaussian Membership Inference Privacy

2023-06-12 · NeurIPS 2023 11 · Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci

We propose a novel and practical privacy notion called $f$-Membership Inference Privacy ($f$-MIP), which explicitly considers the capabilities of realistic adversaries under the membership inference attack threat model. …

Inference AttackMembership Inference Attack