Jul 2026· 2026 6th International Conference on Inventive Computation and Information Technologies (ICICIT)· pp. 1275-1280· 0 citations· 19 references
Abstract
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.
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.
D. Panagoulias, Evangelia-Aikaterini Tsichrintzi, E. Sakkopoulos· International Conference on...· 0 citations
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.
Ze-Yang Zhu, Matthias N. Louws, Roland V. Bumbuc et al.· 0 citations
This paper empirically evaluates ChatGPT 3.5 and 4.0 using over 23,000 real user-generated medical queries, assessing their susceptibility to privacy breaches through quasi-identifiers such as age, location, phone number and national registration number and proposes a scalable privacy evaluation model that combines k-anonymity, l-diversity, t-closeness, entropy, re-identification risk and delta-disclosure.
Foad Jalali, Mehran Alidoost Nia· Journal of Supercomputing· 0 citations
Privacy-preserving synthesis of electronic health records is difficult because clinical data combine continuous measurements, categorical diagnoses, class imbalance, missingness, and multiple trust boundaries. PrivMedSynth is presented as a conditional diffusion framework for mixed type tabular health records in Medical Internet of Things edge cloud environments. The framework applies a local randomizer before transmission and trains a conditional diffusion model with differentially private stochastic gradient descent in the cloud. Continuous features are perturbed with a calibrated Gaussian mechanism, categorical variables are protected with generalized randomized response, and clinical conditions are used as explicit generation controls. Rényi differential privacy accounts for repeated cloud updates and is converted to an approximate differential privacy guarantee. The revised formulation distinguishes the formal privacy guarantee from empirical membership inference performance and makes the privacy unit, adjacency relation, modality budget, and noise parameterization explicit. The experiments report a total variation distance of 0.041, a downstream AUROC of 0.884, and a membership inference AUROC of 0.503 on MIMIC III. These utility and attack results remain conditional on the stated preprocessing and require reproduction under the corrected accounting before being interpreted as a final end to end guarantee. The framework provides a principled basis for studying the privacy and utility tradeoff in distributed synthetic clinical data generation.
A federated deep learning framework that systematically integrates adaptive privacy noise mechanisms and trust-weighted aggregation within a distributed architecture that ensures the protection of sensitive data during collaborative analysis through precise differential privacy control and advanced neural network models is presented.
This work presents and evaluates a privacy-preserving recommendation framework that combines federated learning, differential privacy, cohort-level modeling, and privacy-aware intelligent agents, offering a scalable approach for next-generation AI-driven retail platforms.
Ranjeet K Jha, Venkata Suresh Gummadilli· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
