Deepfake and Voice Clone Identity Shield System

Synthetic videos and cloned voices can be easily created nowadays, and are being used for impersonation, fraud and spreading misinformation.Manually determining whether video content or audio has been manipulated is not reliable.The Deepfake and Voice Clone Identity Shield System (DFVCISS) is a web-based solution that provides detection of video deepfakes, analysis of voice clones and combined audio/video analysis using a single Flask application.It will provide predictions, confidence and evidence from the model instead of just a category.All analysis will be logged within an SQLite history.A PDF can then be generated using the information stored.The video detection uses a trained convolutional neural network.Inspection of the FakeAVCeleb dataset was performed to determine audio/video examples.This project is a prototype to allow initial verification of media.The reliability of the results depend upon the models being used, training dataset and independent testing.

Authors

Publication Details

Journal
IJARCCE
Published
2026-11-16
DOI
https://doi.org/10.17148/ijarcce.2026.1511134
Primary Topic
Digital Media Forensic Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Deepfake and Voice Clone Identity Shield System

Nishmitha H P, Jisha P, Harshitha M R, Navya K L et al.
3 links
IJARCCE
Digital Media Forensic Detection
article

Deepfake and Voice Clone Identity Shield System

Nishmitha H P, Jisha P, Harshitha M R, Navya K L, Dhananjaya M
article en

Abstract

Synthetic videos and cloned voices can be easily created nowadays, and are being used for impersonation, fraud and spreading misinformation.Manually determining whether video content or audio has been manipulated is not reliable.The Deepfake and Voice Clone Identity Shield System (DFVCISS) is a web-based solution that provides detection of video deepfakes, analysis of voice clones and combined audio/video analysis using a single Flask application.It will provide predictions, confidence and evidence from the model instead of just a category.All analysis will be logged within an SQLite history.A PDF can then be generated using the information stored.The video detection uses a trained convolutional neural network.Inspection of the FakeAVCeleb dataset was performed to determine audio/video examples.This project is a prototype to allow initial verification of media.The reliability of the results depend upon the models being used, training dataset and independent testing.

IJARCCEVol. 15(11)
Digital Media Forensic Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon