Skip to content
Conference Open access

A Deception-Based Framework for Brute-Force-Resistant Medical Data Security

Sep 2026 · 2026 International Conference on Secure IoT and Cybersecurity (ICOSICS) · pp. 1-8 · 0 citations · 8 references

Abstract

There are difficulties in securing patient records in digital healthcare settings where patient medical reports and diagnostic images have to be sent through possibly untrusted networks. Single-layer approaches for security may have some flaws due to vulnerability to brute force attacks on keys. We introduce a hybrid approach to secure patient records with a six-layer pipeline including lossless GZIP compression, AES-CFB encryption, binary payload assembly, HMAC-SHA256 validation of the payload integrity, DTE Honey Encryption and LSB image steganography. In case of providing the wrong key, the algorithm provides a valid medical report from another person instead of showing an error message, thus, making brute force attack impossible. Both the encrypted record and diagnostic image become an authenticated payload that is hidden inside the cover image using LSB steganography technique. Keys are generated automatically when the record is created based on a fixed sixteen-letter alphabet without requiring choosing keys manually. Decryption process needs two keys simultaneously and provides valid decoy record in case of entering one wrong key. The keyspace comprises approximately ${2}^{\wedge} {97}$ possible combinations, providing no distinguishable indication between valid and incorrect decryption attempts. After embedding, the cover image achieved a PSNR of 51.14 dB and an SSIM of 0.9998, with no bytes lost during correct-key decryption. Across 500 automated wrong-key trials, all attempts produced decoy records without accessing the original record, with a mean decryption time of 66.234 ms $(\text{SD} = 16.915 ~ \text{ms})$.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.