Decision Tree-Based Synthetic Data Generation Framework for Privacy-Preserving Data Publishing

User-Aware Deep Learning Anonymization for Enhanced Privacy in Medical Record Sharing

As medical records are shared for research and treatment, the same anonymization techniques are used for all, but the risks are exacerbated by the fact that the records are being shared with others. This paper proposes a user-aware deep learning anonymization framework to adjust privacy strength according to the recipient attributes (such as the role, purpose, trust level). It combines conditional generative adversarial networks with differential privacy, with the privacy budget allocated to a user, ε, being tighter for low-trust requesters, and looser for clinicians, where ε ∈ {0.1, 1.0, 5.0}. The proposed approach performs well downstream in terms of the F1 score (0.89) of high-trust users, and exhibits membership inference AUC of 0.52 just above random guessing on the MIMIC-IV data. The accuracy of attribute inference for low-trust users is also low (still less than 0.55) for sensitive diagnoses, leading to improved performance over fixed-DP GAN, AnomiGAN, and PRIMIS. A user encoder is able to decrease mutual information between embeddings and raw patient data from 0.42 to 0.07 during training. In conclusion, the results show that user-adaptive anonymization maintains clinically meaningful utility for legitimate use while ensuring strong protection against re-identification attempts, thereby filling a crucial gap in the field of privacy-preserving medical data sharing.

Embedding-Space Anonymization for Privacy-Preserving AI Systems

This paper studies embedding-space privacy as a representation-level learning problem. Rather than altering raw records directly, the proposed framework applies embeddingspace transformation to full-record representations through Gaussian perturbation and adversarial representation sanitization. The method is evaluated through ablation across utility metrics, linkage attacks, attribute-inference attacks, and membership-inference tests. The primary empirical evaluation uses a synthetic fusion recommendation benchmark built from MovieLens [1], [2] 32M behavior and Adult-derived demographics [3], while a secondary synthetic medical benchmark is used to examine cross-domain transferability under more constrained conditions. The strongest results appear in the recommendation experiments. Under grouped demographic privacy evaluation, the combined condition preserves recommendation utility with $N D C G {@} K=0.6312$ while reducing exact and entity linkage from 0.7090/0.7204 to 0.0001/0.0000. Sensitive-target attacker performance remains near the majority baseline, supporting the claim of empirical privacy improvement without visible ranking degradation in that benchmark. The healthcare experiments also demonstrate meaningful embedding transformation and linkage reduction, though the current benchmark remains datalimited and therefore less conclusive for utility-focused evaluation. Overall, the findings support the conclusion that embeddingspace transformation can preserve downstream utility while substantially reducing linkage risk and sensitive-information recoverability under explicit attacker evaluation. The findings support embedding-space transformation as a practical privacypreserving strategy for embedding-driven AI systems under explicit attacker evaluation.

Privacy-Preserving Feature Engineering Framework for Real-World Vulnerability Risk Prediction

This study introduces a privacy-preserving data preparation and feature engineering framework designed for machine learning-based cybersecurity vulnerability risk prediction, utilizing real-world enterprise scan data from an operational cloud environment. To transform raw vulnerability records into a structured, machine-readable format while complying with personal data protection regulations, the framework integrates systematic data cleaning, missing value imputation, categorical encoding, text normalization, and host pseudonymization. Exploratory data analysis (EDA) was conducted on 36,940 operational records to examine dataset characteristics, vulnerability distributions, and severe class imbalances. Multiple classifiers—including Logistic Regression, Random Forest, XGBoost, and LightGBM—were evaluated under extreme imbalance conditions mitigated via SMOTE. Experimental results demonstrate that non-linear tree-based ensembles achieved the highest predictive performance, with LightGBM attaining a macro F1-score of 0.9974. Comparative analysis further indicates that the effectiveness of textual representations depends on the underlying classifier architecture, with semantic embeddings yielding the best performance when combined with tree-based ensemble models, while TF-IDF remained competitive for linear classification. These findings underscore the critical role of structured text preparation and semantic representation in enhancing model reliability, interpretability, and scalability for automated vulnerability prioritization.

FAIR and Square: Privacy Compliance Framework for Healthcare Databases

Initial evaluations using various machine-learning algorithms on pre-and post-generalized datasets demonstrate the privacy framework’s effectiveness in mitigating privacy risks while preserving data usability.

Privacy-Preserving GAN for Synthetic Data against Membership Inference Attack

High-quality data are essential for machine learning and data-driven research, yet data scarcity and privacy concerns remain major obstacles in many domains. Generative models have recently emerged as a promising approach to synthesize data that follow the same statistical distribution as real datasets. However, generative models are vulnerable to membership inference attacks, which threaten data confidentiality by exploiting model outputs to infer whether specific samples were used in training. Existing defense strategies struggle to simultaneously preserve data utility and provide robust privacy protection. To address this challenge, we propose our PPGM-GAN, a Privacy-Preserving GAN for synthetic data against membership inference attack to balance both data utility and data privacy. PPGM-GAN balances privacy and utility through a privacy-utility tradeoff function that quantifies and optimizes both aspects under different adversarial knowledge. To enhance data utility, we incorporate conditional generation and key-attribute screening to ensure sufficient representation of infrequent attribute values. Additionally, differential privacy is employed during training to prevent overfitting and reduce privacy leakage. Experimental results demonstrate that PPGM-GAN outperforms state-of-the-art privacy-preserving generative models, producing high-utility synthetic data under the same privacy constraints.

[Comparing synthetic data generation methods in pharmacoepidemiology: reconciling reproducibility with privacy protection].