•  
  •  
 

Corresponding Author ORCID Identifer

Xinyi Loi https://orcid.org/0009-0000-7195-9030
Yuk Yii Chan https://orcid.org/0009-0004-0627-6427

Section

Regular Issue

Abstract

Commonly used file-sharing systems suffer from impermissible security risks such as impersonation, credential theft, and QR code exploitation, which can expose sensitive information. This paper describes and evaluates an AI-driven secure file-sharing system designed to alleviate these risks through a multi-layered authentication strategy. The complete system involves AES-128 encryption, unique QR code referencing, live facial recognition, and One-Time Password (OTP) confirmation. In our proposed workflow, the sender encrypts a reference to the file and links it to facial data of the recipient, if applicable, and embeds this information into a QR code, that is dynamically generated during the send operation. To gain access to the file, the user must scan the QR code, undergo live biometric access verification, and subsequently enter an OTP sent to their email address. Experimental results give confidence in the high level of efficacy and robustness of the system: The facial recognition component achieved 99.0% facial recognition accuracy under optimal conditions and achieved 100% rejection against static image spoofing attacks. The average end-to-end server-side latency was about 3.25 seconds, confirming the system would be viable for file sharing. This method combines strong encryption with two-factor identity verification to guarantee confidentiality, mitigate the use of reusable tokens, and provide a secure way to share sensitive documents across a range of sectors, such as healthcare, education, and legal services. The next iteration will be enhanced with liveness detection, dynamic QR codes, and an app to facilitate the entire process of verification, tokenization, and share sensitive documents.

Download

Share

COinS