| Title | Privacy vs Accuracy Trade-Off in Privacy Aware Face Recognition in Smart Systems |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Abbasi, Wisam, Mori, Paolo, Saracino, Andrea, Frascolla, Valerio |
| Conference Name | 2022 IEEE Symposium on Computers and Communications (ISCC) |
| Date Published | jun |
| Keywords | AI, artificial intelligence, Computers, data privacy, Face detection, face recognition, human factors, Optimization, privacy, Privacy Preserving Data Analysis, pubcrawl, resilience, Resiliency, Scalability, Trustworthy AI |
| Abstract | This paper proposes a novel approach for privacy preserving face recognition aimed to formally define a trade-off optimization criterion between data privacy and algorithm accuracy. In our methodology, real world face images are anonymized with Gaussian blurring for privacy preservation. The anonymized images are processed for face detection, face alignment, face representation, and face verification. The proposed methodology has been validated with a set of experiments on a well known dataset and three face recognition classifiers. The results demonstrate the effectiveness of our approach to correctly verify face images with different levels of privacy and results accuracy, and to maximize privacy with the least negative impact on face detection and face verification accuracy. |
| DOI | 10.1109/ISCC55528.2022.9912465 |
| Citation Key | abbasi_privacy_2022 |
Privacy vs Accuracy Trade-Off in Privacy Aware Face Recognition in Smart Systems