Privacy-Preserving Social Media Forensic Analysis for Preventive Policing of Online Activities

Abstract

Social media is extensively used nowadays and is gaining popularity among the users with the increasing growth in the network capacity, connectivity, and speed. Moreover, affordable prices of data plans, especially mobile data packages, have considerably increased the use of multimedia by different users. This includes terrorists who use social media platforms to promote their ideology and intimidate their adversaries. It is therefore very important to develop automated solutions to semantically analyse given multimedia contents to assist law enforcement agencies in the preventive policing of online activities. A major challenge for the social media forensic analysis is to preserve the privacy of citizens who use online social networking platforms. This paper presents results of European H2020 project RED-Alert that aims to enable secure and privacy preserving data processing; hence the malicious content and the corresponding personality can be tracked while the privacy of innocent citizens can be preserved. We have mined seven social media channels for content and providing support for ten languages for analysis. Our proposed solution is designed to ensure security and policing of online contents by detecting terrorist material. We have used speech recognition, face and object detection besides audio event detection to extract information from multimedia files. We have applied anonymization techniques to ensure the privacy of citizens using social media. We have discussed the challenges and prospects of this work especially the need of using digital forensic techniques while respecting European and national data protection laws notably GDPR.