A5082241283- Cancer Genomics and Diagnostics
- Cryptography and Data Security
- Face recognition and analysis
- Algorithms and Data Compression
- Privacy-Preserving Technologies in Data
- Chaos-based Image/Signal Encryption
- Biometric Identification and Security
- Genomic variations and chromosomal abnormalities
- Forensic and Genetic Research
- Face and Expression Recognition
Wuhan University of Technology
2021-2022
Detecting the gene sequence of virus strains from patients and classifying them into specific are very important to provide effective treatment. However, there significant barriers sharing strains' data in plaintext privacy concerns patients. Homomorphic encryption is a form that allows users calculate encrypted without decrypting it. Achieving highly accurate viral strain prediction while safeguarding user challenge. We develop secure multi-label classification method using homomorphic...
The leakage of the face template leads to severe security problems since facial image is unique and irreplaceable each individual. Many researchers have been devoted protecting template. Nevertheless, achieve high for template, partial matching accuracy usually sacrificed. main challenge this problem low inter-user variations intra-user images. In work, we propose a method integrating residual learning error-correcting codes protection. particular, proposed consists two major components: (a)...
The tumor classification based on the correlation between genomic information and tumors plays a vital role in early cancer diagnosis treatment. Patients can outsource to cloud platform for diagnosis. However, anyone who has access obtain these genetic data stored plaintext, patients' privacy cannot be guaranteed. By employing homomorphic encryption technology, directly perform operations gene ciphertext, ensuring privacy. This work proposes several fast, secure models using multi-layer...