Peer-reviewed research at the intersection of cybersecurity, IoT and healthcare — published by IEEE.
Subhabrata Khara et al.
Safeguarding the security and confidentiality of medical data is vital in today's healthcare landscape. This study introduces a hybrid framework that combines encryption and steganography to protect sensitive medical information. Using the Fernet symmetric encryption algorithm, medical data is securely encrypted before being embedded into digital images via Least Significant Bit (LSB) and edge-based data hiding — keeping encrypted data imperceptible while preserving image quality for diagnostic purposes. The framework addresses data integrity, confidentiality, and resilience against attacks, making it highly suitable for electronic health records (EHRs) and telemedicine, achieving robust security with high embedding capacity and minimal distortion.
Secured sensitive medical data in IoMT environments — EHRs, telemedicine streams, and connected devices vulnerable to interception.
Combined Fernet symmetric encryption with steganography — encrypting data, then embedding it invisibly in images via LSB and edge-based hiding.
Robust dual-layer security with high embedding capacity and minimal image distortion — medical images stay diagnostically usable.
Published at ICCMC 2025. Meets stringent healthcare data regulations (HIPAA-aligned) for hospitals and remote patient monitoring.
Deep learning-based steganalysis detection resistance.
AI/ML anomaly detection in real-time IoMT streams.
Federated learning for privacy-preserving medical AI.
Blockchain-based audit trails for EHR systems.
Take a quick break — pick a game.
Tap the bugs as they appear. You have 30 seconds — how many can you squash?
Your move — tap any square.