Back close

Enhancing Healthcare Image Record Security via CNN-based Tamper Detection

Publication Type : Conference Paper

Publisher : IEEE

Source : 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS)

Url : https://doi.org/10.1109/ICSSAS64001.2024.10760451

Keywords : Deepfakes; Solid modeling; Accuracy; Three-dimensional displays; Watermarking; Predictive models; Real-time systems; Medical diagnostic imaging; Digital signatures; Surface treatment; Electronic Health Records; Convolutional Neural Networks; Watermarking; Digital Imaging and Communication in Medicine; Digital Signatures; Deep Learning; Tamper Detection

Campus : Bengaluru

School : School of Computing

Department : Computer Science and Engineering

Year : 2024

Abstract : Computers have been seamlessly integrated into every domain including health care where one of its applications is in the storage of health care records such as medical images. Electronic healtheare records contain a lot of sensitive information about patients, such as the diseases, diagnosis, treatment plans, drugs administered or medicines prescribed and hence this vital information must not be disclosed at any cost as it can have huge repercussions. As each day passes, more vulnerabilities and threats surface and it is important to come up with secure systems and apt security measures to counter these threats and keep the attackers at bay. This study provides a holistic approach to secure and safeguard medical image records by addressing two problems, the first is image tamper detection using medical image deepfake detection to decipher whether the image has been modified or not, and the second is to employ various cryptographic techniques such as hashing, watermarking and digital signatures to protect the images from getting tampered itself.

Cite this Research Publication : U Kumaran, Gurupriya M, Harshitha Reddy Thodathara, Aryagopal, Aditya Vijjapu, Gattamaneni Harish, Enhancing Healthcare Image Record Security via CNN-based Tamper Detection, [source], IEEE, 2024, https://doi.org/10.1109/ICSSAS64001.2024.10760451

Admissions Apply Now