Cover Image

Optimizing Canaries for Privacy Auditing with Metagradient Descent

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Boglioni, Matteo, Liu, Terrance, Ilyas, Andrew, Wu, Zhiwei Steven
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
by: Liu, Terrance, et al.
Published: (2025)

Generate-then-Verify: Reconstructing Data from Limited Published Statistics
by: Liu, Terrance, et al.
Published: (2025)

The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
by: Meeus, Matthieu, et al.
Published: (2025)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
by: Wu, Xiaoyu, et al.
Published: (2025)

Observational Auditing of Label Privacy
by: Kalemaj, Iden, et al.
Published: (2025)

Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
by: Wu, Xiaoyu, et al.
Published: (2025)

Visual Privacy Auditing with Diffusion Models
by: Schwethelm, Kristian, et al.
Published: (2024)

The Sample Complexity of Membership Inference and Privacy Auditing
by: Haghifam, Mahdi, et al.
Published: (2025)

Auditing $f$-Differential Privacy in One Run
by: Mahloujifar, Saeed, et al.
Published: (2024)

Optimizing ML Training with Metagradient Descent
by: Engstrom, Logan, et al.
Published: (2025)

Sequentially Auditing Differential Privacy
by: González, Tomás, et al.
Published: (2025)

Auditing Differential Privacy Guarantees Using Density Estimation
by: Koskela, Antti, et al.
Published: (2024)

Auditing Privacy Mechanisms via Label Inference Attacks
by: Busa-Fekete, Róbert István, et al.
Published: (2024)

How Well Can Differential Privacy Be Audited in One Run?
by: Keinan, Amit, et al.
Published: (2025)

PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
by: Kazmi, Mishaal, et al.
Published: (2024)

Auditing Differential Privacy in the Black-Box Setting
by: Shi, Kaining, et al.
Published: (2025)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
by: Cebere, Tudor, et al.
Published: (2024)

Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis
by: Ward, Joshua, et al.
Published: (2025)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
by: Yoon, Sangyeon, et al.
Published: (2024)

Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability
by: Sahani, Mukesh, et al.
Published: (2025)

Tight Auditing of Differential Privacy in MST and AIM
by: Ganev, Georgi, et al.
Published: (2026)

Membership Inference Attacks for Unseen Classes
by: Thaker, Pratiksha, et al.
Published: (2025)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
by: Zhang, Xinwei, et al.
Published: (2023)

On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
by: Thaker, Pratiksha, et al.
Published: (2023)

Auditing Privacy in Multi-Tenant RAG under Account Collusion
by: Burnat, Florian A. D.
Published: (2026)

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent
by: Yu, Da, et al.
Published: (2022)

Privacy Vulnerabilities in Marginals-based Synthetic Data
by: Golob, Steven, et al.
Published: (2024)

TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning
by: Wang, Weiqi, et al.
Published: (2025)

Empirical Privacy Variance
by: Hu, Yuzheng, et al.
Published: (2025)

Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
by: Mandal, Bishwas, et al.
Published: (2024)

Revisiting Hyperparameter Tuning with Differential Privacy
by: Ding, Youlong, et al.
Published: (2022)

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
by: Bertran, Martin, et al.
Published: (2024)

Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication
by: Ma, Xirong
Published: (2023)

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking
by: Zhao, Yizhou, et al.
Published: (2025)

Agentic Privacy-Preserving Machine Learning
by: Zhang, Mengyu, et al.
Published: (2025)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks
by: Luo, Jiayi, et al.
Published: (2025)

Local Differential Privacy in Graph Neural Networks: a Reconstruction Approach
by: Bhaila, Karuna, et al.
Published: (2023)