Embedded Files
DEFENCE: Data-driven harmful content detection system
DEFENCE: Data-driven harmful content detection system
Principal Investigator: Ciprian-Octavian TRUICĂ
Principal Investigator: Ciprian-Octavian TRUICĂ
Funding Agency: UEFISCDI
Funding Agency: UEFISCDI
Program: ROFR2025
Program: ROFR2025
Grant no.: 18BMFR/06.07.2026
Grant no.: 18BMFR/06.07.2026
Overview
Overview
DEFENCE aims to develop a data-driven system using deep learning models to automatically detect and mitigate the spread of harmful content, such as misinformation and abusive speech, on social media. Additionally, the research investigates whether such harmful behavior transcends various social, cultural, political, and economic factors.
Key Objectives
Key Objectives
Design data-driven artificial intelligence models to detect harmful content spread on social media.
Determine whether the spread of harmful content transcends social, cultural, political, and economic factors
Innovation and Impact
Innovation and Impact
NetGuardAI pioneers advanced deep learning models to automatically detect antisocial behavior and harmful content while analyzing whether such malicious patterns transcend social, cultural, political, and economic boundaries. By curbing the spread of misinformation, propaganda, and abusive speech on online platforms, the system effectively protects public discourse and reduces the societal harm caused by malicious actors.
Publications
Publications
Journals
Journals
2026
2026
TBA
Conferences
Conferences
2026
2026
TBA
Software
Software
TBA
LLM Models
LLM Models
TBA
Page updated
Google Sites
Report abuse