Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety

Abstract In today’s digital environment, effectively detecting and censoring harmful and offensive objects such as weapons, addictive substances, and violent content on online platforms is increasingly important for user safety. This study introduces an Enhanced Object Detection (EOD) model that bui...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammed Kawser Jahan, Fokrul Islam Bhuiyan, Al Amin, M. F. Mridha, Mejdl Safran, Sultan Alfarhood, Dunren Che
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-08413-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849402634232922112
author Mohammed Kawser Jahan
Fokrul Islam Bhuiyan
Al Amin
M. F. Mridha
Mejdl Safran
Sultan Alfarhood
Dunren Che
author_facet Mohammed Kawser Jahan
Fokrul Islam Bhuiyan
Al Amin
M. F. Mridha
Mejdl Safran
Sultan Alfarhood
Dunren Che
author_sort Mohammed Kawser Jahan
collection DOAJ
description Abstract In today’s digital environment, effectively detecting and censoring harmful and offensive objects such as weapons, addictive substances, and violent content on online platforms is increasingly important for user safety. This study introduces an Enhanced Object Detection (EOD) model that builds upon the YOLOv8-m architecture to improve the identification of such harmful objects in complex scenarios. Our key contributions include enhancing the cross-stage partial fusion blocks and incorporating three additional convolutional blocks into the model head, leading to better feature extraction and detection capabilities. Utilizing a public dataset covering six categories of harmful objects, our EOD model achieves superior performance with precision, recall, and mAP50 scores of 0.88, 0.89, and 0.92 on standard test data, and 0.84, 0.74, and 0.82 on challenging test cases–surpassing existing deep learning approaches. Furthermore, we employ explainable AI techniques to validate the model’s confidence and decision-making process. These advancements not only enhance detection accuracy but also set a new benchmark for harmful object detection, significantly contributing to the safety measures across various online platforms.
format Article
id doaj-art-1c7fa093996b449da3689a669efb50fa
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1c7fa093996b449da3689a669efb50fa2025-08-20T03:37:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-08413-4Enhancing the YOLOv8 model for realtime object detection to ensure online platform safetyMohammed Kawser Jahan0Fokrul Islam Bhuiyan1Al Amin2M. F. Mridha3Mejdl Safran4Sultan Alfarhood5Dunren Che6Department of Computer Science, American International University-BangladeshDepartment of Computer Science, American International University-BangladeshDepartment of Computer Science, American International University-BangladeshDepartment of Computer Science, American International University-BangladeshResearch Chair of Online Dialogue and Cultural Communication, Department of Computer Science, College of Computer and Information Sciences, King Saud UniversityResearch Chair of Online Dialogue and Cultural Communication, Department of Computer Science, College of Computer and Information Sciences, King Saud UniversityDepartment of Electrical Engineering and Computer Science, Texas A&M University-KingsvilleAbstract In today’s digital environment, effectively detecting and censoring harmful and offensive objects such as weapons, addictive substances, and violent content on online platforms is increasingly important for user safety. This study introduces an Enhanced Object Detection (EOD) model that builds upon the YOLOv8-m architecture to improve the identification of such harmful objects in complex scenarios. Our key contributions include enhancing the cross-stage partial fusion blocks and incorporating three additional convolutional blocks into the model head, leading to better feature extraction and detection capabilities. Utilizing a public dataset covering six categories of harmful objects, our EOD model achieves superior performance with precision, recall, and mAP50 scores of 0.88, 0.89, and 0.92 on standard test data, and 0.84, 0.74, and 0.82 on challenging test cases–surpassing existing deep learning approaches. Furthermore, we employ explainable AI techniques to validate the model’s confidence and decision-making process. These advancements not only enhance detection accuracy but also set a new benchmark for harmful object detection, significantly contributing to the safety measures across various online platforms.https://doi.org/10.1038/s41598-025-08413-4Harmful object detectionVisual censorship systemsGraphic violenceInsulting gestureYOLOv8
spellingShingle Mohammed Kawser Jahan
Fokrul Islam Bhuiyan
Al Amin
M. F. Mridha
Mejdl Safran
Sultan Alfarhood
Dunren Che
Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
Scientific Reports
Harmful object detection
Visual censorship systems
Graphic violence
Insulting gesture
YOLOv8
title Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
title_full Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
title_fullStr Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
title_full_unstemmed Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
title_short Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety
title_sort enhancing the yolov8 model for realtime object detection to ensure online platform safety
topic Harmful object detection
Visual censorship systems
Graphic violence
Insulting gesture
YOLOv8
url https://doi.org/10.1038/s41598-025-08413-4
work_keys_str_mv AT mohammedkawserjahan enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT fokrulislambhuiyan enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT alamin enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT mfmridha enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT mejdlsafran enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT sultanalfarhood enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety
AT dunrenche enhancingtheyolov8modelforrealtimeobjectdetectiontoensureonlineplatformsafety