Operation Bedside‑Breach: When Hackers Meet Hospital Beds. Algorithmic Ransomware Detection and Encryption Benchmarking

Overview

Because ransomware can disrupt life‑critical bedside telemetry and threaten pediatric patient safety, I developed and validated a lightweight, real‑time entropy‑based ransomware detection engine for pediatric IoMT devices. I implemented the detector in Python and deployed it on Raspberry Pi 4 testbeds, using sliding‑window Shannon entropy monitoring, dynamic thresholding, and ELK‑backed logging; controlled experiments (1000 trials) compared benign telemetry to scripted ransomware bursts from multiple families and benchmarked AES, RSA, and ChaCha20 for latency and resource impact. The detector achieved 92% accuracy, <2% false positives, AUC = 0.95 (p < 0.001), and consistent detection latency <50 ms; ChaCha20 showed the best performance (5–6 ms latency, 10–15% CPU). All testing was performed in an isolated lab, and these results indicate the approach can substantially reduce ransomware‑related device downtime, minimize clinical disruption to bedside telemetry, and provide a low‑overhead, scalable pathway for integrating device‑level defenses into hospital monitoring infrastructures while motivating broader clinical validation.

Competition history

• CSEF 2026 Computational Science (Senior Division) · Entry S-07-05

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Computational Sciences projects
• CSEF Computational Sciences projects
• Every CSEF 2026 project