Cover Image

Generate-then-Verify: Reconstructing Data from Limited Published Statistics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Terrance, Xiao, Eileen, Smith, Adam, Thaker, Pratiksha, 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)

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

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

Lower Bounds for Public-Private Learning under Distribution Shift
by: Setlur, Amrith, et al.
Published: (2025)

Optimizing Canaries for Privacy Auditing with Metagradient Descent
by: Boglioni, Matteo, et al.
Published: (2025)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
by: Wu, Xiaoyu, 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)

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

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

Oracle-Efficient Differentially Private Learning with Public Data
by: Block, Adam, et al.
Published: (2024)

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
by: Brown, Gavin, et al.
Published: (2024)

Verifying LLM Inference to Detect Model Weight Exfiltration
by: Rinberg, Roy, et al.
Published: (2025)

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

Privacy-Preserving Statistical Data Generation: Application to Sepsis Detection
by: Macias-Fassio, Eric, et al.
Published: (2024)

Nonparametric extensions of randomized response for private confidence sets
by: Waudby-Smith, Ian, et al.
Published: (2022)

Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
by: Krüger, Fabian P., et al.
Published: (2024)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
by: Liu, Sheng, et al.
Published: (2024)

Verifiable Unlearning on Edge
by: Maheri, Mohammad M, et al.
Published: (2025)

A User-Centric, Privacy-Preserving, and Verifiable Ecosystem for Personal Data Management and Utilization
by: Zafar, Osama, et al.
Published: (2025)

MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs
by: Wu, Zhenpeng, et al.
Published: (2024)

FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
by: Meerza, Syed Irfan Ali, et al.
Published: (2026)

Data Reconstruction: Identifiability and Optimization with Sample Splitting
by: Shen, Yujie, et al.
Published: (2026)

Training Data Reconstruction: Privacy due to Uncertainty?
by: Runkel, Christina, et al.
Published: (2024)

ZKBoost: Zero-Knowledge Verifiable Training for XGBoost
by: Melissaris, Nikolas, et al.
Published: (2026)

Bayesian Pseudo Posterior Mechanism for Differentially Private Machine Learning
by: Chew, Robert, et al.
Published: (2025)

SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark
by: Wen, Rui, et al.
Published: (2025)

On the Query Complexity of Training Data Reconstruction in Private Learning
by: Mukherjee, Prateeti, et al.
Published: (2023)

Pre-training Differentially Private Models with Limited Public Data
by: Bu, Zhiqi, et al.
Published: (2024)

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

Privacy-Preserving Verifiable Neural Network Inference Service
by: Riasi, Arman, et al.
Published: (2024)

Expressive Losses for Verified Robustness via Convex Combinations
by: De Palma, Alessandro, et al.
Published: (2023)

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
by: Yao, Duanyi, et al.
Published: (2024)

Federated Learning Nodes Can Reconstruct Peers' Image Data
by: Wilson, Ethan, et al.
Published: (2024)

Covert Quantum Learning: Privately and Verifiably Learning from Quantum Data
by: Anand, Abhishek, et al.
Published: (2025)

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
by: Pal, Arka, et al.
Published: (2026)

Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates
by: Yue, Kai, et al.
Published: (2025)

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

Verifying Classification with Limited Disclosure
by: Bhandari, Siddharth, et al.
Published: (2025)

Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
by: Zhang, Jiale, et al.
Published: (2025)

Game-Theoretic Unlearnable Example Generator
by: Liu, Shuang, et al.
Published: (2024)