Facial Image Encryption for Secure Face Recognition System
A biometric authentication system is more convenient and secure than graphical or textual passwords when accessing information systems. Unfortunately, biometric authentication systems have the disadvantage of being susceptible to spoofing attacks. Authentication schemes based on biometrics, includin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/3/774 |
| _version_ | 1797624766836768768 |
|---|---|
| author | Eimad Abusham Basil Ibrahim Kashif Zia Muhammad Rehman |
| author_facet | Eimad Abusham Basil Ibrahim Kashif Zia Muhammad Rehman |
| author_sort | Eimad Abusham |
| collection | DOAJ |
| description | A biometric authentication system is more convenient and secure than graphical or textual passwords when accessing information systems. Unfortunately, biometric authentication systems have the disadvantage of being susceptible to spoofing attacks. Authentication schemes based on biometrics, including face recognition, are susceptible to spoofing. This paper proposes an image encryption scheme to counter spoofing attacks by integrating it into the pipeline of Linear Discriminant Analysis (LDA) based face recognition. The encryption scheme uses XOR pixels substitution and cellular automata for scrambling. A single key is used to encrypt the training and testing datasets in LDA face recognition system. For added security, the encryption step requires input images of faces to be encrypted with the correct key before the system can recognize the images. An LDA face recognition scheme based on random forest classifiers has achieved 96.25% accuracy on ORL dataset in classifying encrypted test face images. In a test where original test face images were not encrypted with keys used for encrypted feature databases, the system achieved 8.75% accuracy only showing it is capable of resisting spoofing attacks. |
| first_indexed | 2024-03-11T09:47:08Z |
| format | Article |
| id | doaj.art-9e0ee7b8cd734267b89c4abbf3ccba9b |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T09:47:08Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9e0ee7b8cd734267b89c4abbf3ccba9b2023-11-16T16:31:18ZengMDPI AGElectronics2079-92922023-02-0112377410.3390/electronics12030774Facial Image Encryption for Secure Face Recognition SystemEimad Abusham0Basil Ibrahim1Kashif Zia2Muhammad Rehman3Faculty of Computing and Information Technology, Sohar University, Sohar 311, OmanFaculty of Computing and Information Technology, Sohar University, Sohar 311, OmanSchool of Health & Wellbeing, University of Glasgow, Glasgow G20 7SB, UKFaculty of Computing and Information Technology, Sohar University, Sohar 311, OmanA biometric authentication system is more convenient and secure than graphical or textual passwords when accessing information systems. Unfortunately, biometric authentication systems have the disadvantage of being susceptible to spoofing attacks. Authentication schemes based on biometrics, including face recognition, are susceptible to spoofing. This paper proposes an image encryption scheme to counter spoofing attacks by integrating it into the pipeline of Linear Discriminant Analysis (LDA) based face recognition. The encryption scheme uses XOR pixels substitution and cellular automata for scrambling. A single key is used to encrypt the training and testing datasets in LDA face recognition system. For added security, the encryption step requires input images of faces to be encrypted with the correct key before the system can recognize the images. An LDA face recognition scheme based on random forest classifiers has achieved 96.25% accuracy on ORL dataset in classifying encrypted test face images. In a test where original test face images were not encrypted with keys used for encrypted feature databases, the system achieved 8.75% accuracy only showing it is capable of resisting spoofing attacks.https://www.mdpi.com/2079-9292/12/3/774face recognitionLDAimage encryptioncellular automata |
| spellingShingle | Eimad Abusham Basil Ibrahim Kashif Zia Muhammad Rehman Facial Image Encryption for Secure Face Recognition System Electronics face recognition LDA image encryption cellular automata |
| title | Facial Image Encryption for Secure Face Recognition System |
| title_full | Facial Image Encryption for Secure Face Recognition System |
| title_fullStr | Facial Image Encryption for Secure Face Recognition System |
| title_full_unstemmed | Facial Image Encryption for Secure Face Recognition System |
| title_short | Facial Image Encryption for Secure Face Recognition System |
| title_sort | facial image encryption for secure face recognition system |
| topic | face recognition LDA image encryption cellular automata |
| url | https://www.mdpi.com/2079-9292/12/3/774 |
| work_keys_str_mv | AT eimadabusham facialimageencryptionforsecurefacerecognitionsystem AT basilibrahim facialimageencryptionforsecurefacerecognitionsystem AT kashifzia facialimageencryptionforsecurefacerecognitionsystem AT muhammadrehman facialimageencryptionforsecurefacerecognitionsystem |