Imagen de Portada

Data Reconstruction: Identifiability and Optimization with Sample Splitting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shen, Yujie, Wang, Zihan, Qian, Jian, Lei, Qi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
por: Pal, Soumyadeep, et al.
Publicado: (2024)

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

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy
por: You, Zhichao, et al.
Publicado: (2025)

DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning
por: Liu, Yixuan, et al.
Publicado: (2024)

Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
por: He, Weiqing, et al.
Publicado: (2026)

Vol-Mark: A Watermark for 3D Medical Volume Data Via Cubic Difference Expansion and Contrastive Learning
por: Zhu, Jiangnan, et al.
Publicado: (2026)

Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation
por: Maddock, Samuel, et al.
Publicado: (2025)

Verification of Machine Unlearning is Fragile
por: Zhang, Binchi, et al.
Publicado: (2024)

Optimal Defenses Against Gradient Reconstruction Attacks
por: Chen, Yuxiao, et al.
Publicado: (2024)

Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
por: Zhang, Yujie, et al.
Publicado: (2024)

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

Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharing
por: Khan, Tanveer, et al.
Publicado: (2025)

The Challenge of Identifying the Origin of Black-Box Large Language Models
por: Yang, Ziqing, et al.
Publicado: (2025)

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness
por: Wang, Cheng-Long, et al.
Publicado: (2024)

HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
por: Qiu, Pengyu, et al.
Publicado: (2022)

A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction
por: Wan, Jialin, et al.
Publicado: (2025)

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

Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams
por: Gower-Winter, Brandon, et al.
Publicado: (2024)

TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
por: Dai, Yanbo, et al.
Publicado: (2025)

Smart Surveillance: Identifying IoT Device Behaviours using ML-Powered Traffic Analysis
por: Ryan, Reza, et al.
Publicado: (2025)

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

SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
por: Erdogan, Ege, et al.
Publicado: (2023)

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

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

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

An Efficient Privacy-aware Split Learning Framework for Satellite Communications
por: Sun, Jianfei, et al.
Publicado: (2024)

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

A Taxonomy of Attacks and Defenses in Split Learning
por: Shabbir, Aqsa, et al.
Publicado: (2025)

Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
por: Furukawa, Sae, et al.
Publicado: (2026)

A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2023)

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
por: Pham, Dzung, et al.
Publicado: (2023)

Osmosis Distillation: Model Hijacking with the Fewest Samples
por: Shi, Yuchen, et al.
Publicado: (2026)

A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
por: Liu, Zihan, et al.
Publicado: (2026)

A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
por: Lei, Yiming, et al.
Publicado: (2026)

Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning
por: Jiang, Yu, et al.
Publicado: (2025)

Hard-Label Cryptanalytic Extraction of Neural Network Models
por: Chen, Yi, et al.
Publicado: (2024)

Passive Inference Attacks on Split Learning via Adversarial Regularization
por: Zhu, Xiaochen, et al.
Publicado: (2023)

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

Graph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation
por: Tan, Zhizhong, et al.
Publicado: (2025)