Cover Image

Bayesian Perspective on Memorization and Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kaplan, Haim, Mansour, Yishay, Nissim, Kobbi, Stemmer, Uri
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Data Reconstruction: When You See It and When You Don't
by: Cohen, Edith, et al.
Published: (2024)

Differentially Private Release and Learning of Threshold Functions
by: Bun, Mark, et al.
Published: (2015)

Private Truly-Everlasting Robust-Prediction
by: Stemmer, Uri
Published: (2024)

Credit Attribution and Stable Compression
by: Livni, Roi, et al.
Published: (2024)

Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold Queries
by: Cohen, Edith, et al.
Published: (2024)

Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems
by: Nissim, Kobbi, et al.
Published: (2025)

OCR-APT: Reconstructing APT Stories from Audit Logs using Subgraph Anomaly Detection and LLMs
by: Aly, Ahmed, et al.
Published: (2025)

Protecting the Undeleted in Machine Unlearning
by: Cohen, Aloni, et al.
Published: (2026)

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

DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization
by: Luo, Xiaoyu, et al.
Published: (2024)

Hot PATE: Private Aggregation of Distributions for Diverse Task
by: Cohen, Edith, et al.
Published: (2023)

Quantifying Memorization and Privacy Risks in Genomic Language Models
by: Nemecek, Alexander, et al.
Published: (2026)

Localizing Paragraph Memorization in Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

Can Copyright be Reduced to Privacy?
by: Elkin-Koren, Niva, et al.
Published: (2023)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
by: Xiong, Alexander, et al.
Published: (2025)

Extracting Memorized Training Data via Decomposition
by: Su, Ellen, et al.
Published: (2024)

Unveiling Privacy, Memorization, and Input Curvature Links
by: Ravikumar, Deepak, et al.
Published: (2024)

Is merging worth it? Securely evaluating the information gain for causal dataset acquisition
by: Fawkes, Jake, et al.
Published: (2024)

Data-centric NLP Backdoor Defense from the Lens of Memorization
by: Wang, Zhenting, et al.
Published: (2024)

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs
by: Joshi, Kunj, et al.
Published: (2025)

Federated Bayesian Network Ensembles
by: van Daalen, Florian, et al.
Published: (2024)

Differentially private Bayesian tests
by: Chakraborty, Abhisek, et al.
Published: (2024)

Learning from Equivalence Queries, Revisited
by: Braverman, Mark, et al.
Published: (2026)

Preliminary Investigation into Uncertainty-Aware Attack Stage Classification
by: Gaudenzi, Alessandro, et al.
Published: (2025)

Position: Privacy Is Not Just Memorization!
by: Mireshghallah, Niloofar, et al.
Published: (2025)

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
by: Wang, Fei, et al.
Published: (2025)

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)

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

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

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

Graph Reconstruction from Differentially Private GNN Explanations
by: Sahoo, Rishi Raj, et al.
Published: (2026)

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

Rethinking Randomized Smoothing from the Perspective of Scalability
by: Kumari, Anupriya, et al.
Published: (2023)

Detection Latencies of Anomaly Detectors: An Overlooked Perspective ?
by: Puccetti, Tommaso, et al.
Published: (2024)

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

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)

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

Personalized Federated Learning of Probabilistic Models: A PAC-Bayesian Approach
by: Boroujeni, Mahrokh Ghoddousi, et al.
Published: (2024)