High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

PaperGuard AI

Author(s):

Vaishnavi Hitesh Bhosale , Zeal Institute, Narhe, Pune; Tejashree Nana Shinde, Zeal Institute, Narhe, Pune; Dhanashri Kailasnath Ekke, Zeal Institute, Narhe, Pune; Akshara Hiralal Rangapure, Zeal Institute, Narhe, Pune, Zeal Institute, Narhe, Pune

Keywords:

PaperGuard, Examination Security, Anomaly Detection, Risk Scoring, AES-256, Forensic Watermark, Access Control

Abstract

PaperGuard is a proposed AI-assisted security framework intended to reduce the risk of examination paper leakage before sensitive content is released. It combines role-based access control, authenticated access, multi-factor authentication, biometric verification, an AI risk engine, AES-256 double encryption, an encrypted cloud vault, forensic watermarking, and secure kiosk-mode display. The AI layer is designed to learn normal access patterns, analyze access telemetry, identify unusual behavior, explain risk factors, and prioritize alerts. A risk score above the proposed 30% threshold triggers review rather than automatic release. Super-Admin approval remains a required human control. The paper describes the proposed architecture and end-to-end workflow from upload to controlled examination access. The design is a project proposal; its effectiveness requires implementation and evaluation.

Other Details

Paper ID: IJSRDV14I90033
Published in: Volume : 14, Issue : 9
Publication Date: 01/12/2026
Page(s): 56-58

Article Preview

Download Article