PriEval-Protect, a two-phase framework for unified privacy risk evaluation and mitigation, demonstrates regulation-aligned, explainable assessments, bridging legal conformance and data-level risk analysis.
Abstract
Safeguarding patient privacy while enabling meaningful healthcare data use remains critical under GDPR and HIPAA. Existing compliance methods are manual, error-prone, and separate policy audits from data-level assessments. This paper presents PriEval-Protect, a two-phase framework for unified privacy risk evaluation and mitigation. The evaluation phase combines regulatory compliance scoring using a fine-tuned legal LLM with RAG, and technical analysis via encryption type, data architecture, and metrics including similarity, uncertainty, adversary success, and information gain/loss. A composite risk score uses weighted aggregation via Analytic Hierarchy Process. The protection phase recommends countermeasures including federated learning and differential privacy based on assessed risk. Results on hospital documents and datasets demonstrate regulation-aligned, explainable assessments, bridging legal conformance and data-level risk analysis.
This work proposes a practical framework for assessing privacy risk in clinical foundation models and illustrates realistic leakage scenarios across deployment settings, map them to legal regimes, and outline complementary technical and legal mitigations.
Sana Tonekaboni, Lena Stempfle, Sasha Ronaghi et al.· 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
The United States healthcare sector grapples with rising cybersecurity threats. Ransomware and data breaches expose millions of protected health information (PHI) records each year, while artificial intelligence (AI) has advanced analytics and supported clinical decisions and tools. AI amplifies both vulnerabilities and protections, but traditional safeguards often struggle or fail to support collaborative model development with stringent HIPAA and HITECH rules. Privacy-preserving machine learning (PPML) techniques offer potential solutions to this tension.
This narrative review draws together peer-reviewed literature from 2020 to 2026 on AI-driven privacy-preserving techniques like federated learning, differential privacy, homomorphic encryption, secure multi-party computation, and blockchain-AI hybrids applied to US healthcare cybersecurity. These tools allow decentralized training, encrypted operations, and auditable partnerships that curb re-identification, inference attacks, and centralized data risks.
Key findings highlight federated learning’s maturity in multi-institutional applications, differential privacy’s solid defenses for group-level analysis, and the promise of hybrids to overcome individual limitations such as computational overhead and expansion barriers. However, persistent challenges include resource demands, potential bias amplification, adversarial vulnerabilities, and limited real-world longitudinal evidence.
The review calls for uniform testing standards, quantum-proof designs, and policy boots to speed uptake. Such methods strengthen privacy alongside function, paving the way for reliable AI use that protects patients, cuts breach damage, and promotes digital health innovation in an increasingly threatened ecosystem.
Isaiah Thompson Ocansey, Mary Magdalene Linda Yeboah· Magna Scientia Advanced Rese...· 0 citations
This paper examines how privacy-enhancing technologies such as synthetic data, federated learning and ‘Secure Data Environments’ can be integrated into artificial intelligence (
AI
) development processes to uphold key data protection principles in the UK
GDPR
, like storage limitation, data minimisation, purpose limitation, security, and fairness. The analysis highlights how privacy-enhancing technologies offer benefits beyond anonymisation by embedding privacy-by-design values to support responsible innovation and protect sensitive patient data throughout the design, training, and validation of medical
AI
systems. The paper uses the 2015 DeepMind and Royal Free case as a practical study to realise the practical and legal benefits of privacy-enhancing technologies in medical
AI
development, particularly involving public-private collaborations. While grounded in the UK context, the findings have broader relevance to the European Union and other international jurisdictions grappling with tensions between data protection and
AI
development in the healthcare context.
Yasmine Zoya· European Journal of Health L...· 0 citations
The digitalization of healthcare increases privacy risks associated with sensitive data processing. Although the Brazilian General Data Protection Law (LGPD) mandates data protection, healthcare organizations often focus on generic security controls and lack structured privacy engineering to address threats such as linkability and identifiability. This paper proposes a privacy threat modeling method for healthcare systems under the LGPD. The method was evaluated through a case study involving the Nursing Process Application System (SisAPEC), a system deployed within the Brazilian Unified Health System (SUS). The method includes system modeling and systematic threat elicitation steps, which in the case study were implemented using Data Flow Diagrams and the LINDDUN framework. The application of the method identified 14 privacy threats, which were mapped to Privacy-Enhancing Requirements (PERs), establishing traceability between regulatory and technical requirements. The results indicate that the method operationalizes Privacy by Design by establishing traceability between legal requirements and architectural privacy requirements.
Giovana N. Oliveira, I. C. P. Costa, R. Aguiar et al.· Anais do LIII Seminário Inte...· 0 citations
Emergency access to Electronic Health Record (EHR) systems presents a difficult balance between protecting sensitive patient information and ensuring that clinicians can obtain critical information without delay. Existing security approaches, including Zero-Trust Architecture (ZTA), multi-factor authentication (MFA), and conventional break-glass mechanisms, primarily rely on user identity, device, or network context and do not consider the patient's current clinical condition. No existing approach uses the patient's real-time clinical deterioration as the signal that drives the access decision, which is the specific gap this study addresses. The novelty of the proposed framework lies in coupling clinical-deterioration prediction directly to Zero-Trust policy enforcement, together with automatic privilege revocation once the patient stabilises, rather than in any single component. This study proposes an AI-driven risk-adaptive Zero-Trust framework that incorporates real-time patient deterioration into access control decisions. An LSTM model analyses five vital signs and classifies patient status as STABLE, WARNING, or CRITICAL. The predicted clinical risk is combined with role-specific emergency authority to calculate a composite risk score that determines one of four access levels: Direct Access, MFA Required, Restricted Access, or Denied. The framework was evaluated using the MIMIC-III Clinical Database Demo, comprising 98 patients and 5,992 NEWS2-labelled time-series sequences, together with 6,000 simulated access requests across six clinical specialities. The proposed model achieved an overall accuracy of 82.20%, a CRITICAL-class recall of 88.00%, and an AUC of 0.9752. The access-control engine produced an average decision latency of 0.265 ms while maintaining complete audit logging and 99.3% least-privilege compliance. These findings suggest that integrating clinical deterioration predictions into Zero-Trust access control can improve emergency responsiveness while preserving security and accountability. Although the framework was evaluated in a simulated environment, the results demonstrate its potential for future deployment and validation in real clinical settings.
Arthur Nashon Malingo, Christian Budoya, G. Tesha· East African Journal of Info...· 0 citations