In the past decade, rapid developments in mass storage architectures and sensing technologies, such as the emergence of social networking websites and wearable devices, have brought about the phenomenon of big data, which involves zettabytes of data being produced every day. New research opportunities and challenges for multimedia content analysis have arisen. Many big data modelling methods, computing algorithms, and signal processing technologies have recently been successfully developed and applied to multimedia social and personal content analysis: for example, multi-view learning algorithms have been proposed for exploring the variety of multimedia content, sparse and manifold learning have been developed for high-dimensional multimedia data representation, deep learning has produced promising results in large scale multimedia retrieval, and compressive sensing and new sampling schemes have been investigated for big data analytics.

The ability to process these unprecedented amounts of data in real time using multimedia analytics tools brings many benefits that can be utilised in cyber threat analysis systems. Cyber threat analysts and intrusion detection/prevention systems can discover useful information in real time by making use of big data collected from networks, computers, sensors, and cloud systems. This information can help detect system vulnerabilities and attacks that are becoming increasingly prevalent and help develop security solutions accordingly. Big data-driven multimedia analytics are effective for security solutions, as features of big data-driven multimedia techniques can discover anomalies and attack patterns as fast as possible, limiting the vulnerability of the systems and increasing their resilience. Motivated by the inclination to collect a set of recent advances and results in these related topics, provide a platform for researchers to exchange their innovative ideas on security and privacy models and techniques for social/personal multimedia analytics, and introduce interesting utilisations of methods and schema for particular social/personal media applications.

The aim of this Special Issue is to attract a broad range of submissions on the development and use of big data-driven multimedia analytics for security and privacy techniques. Motivated by the inclination to collect a set of recent advances and results in these related topics, we aim to provide a platform for researchers to exchange their innovative ideas on security and privacy models and techniques for social/personal multimedia analytics, and introduce interesting utilisations of methods and schema for particular social/personal media applications. Both original research and review articles are welcome, including papers on theoretical advances in security and privacy, as well as algorithm developments in big data technology for media analytics problems

Potential topics include but are not limited to the following:

• Big data-driven multimedia analytics for intrusion detection
• Big data analytics for cloud system security
• Visualisation with big data multimedia analytics
• Malware detection using big data multimedia analytics
• Cyber threat intelligence using big data multimedia analytics
• Big data processing architectures for threat detection
• Advanced persistent threat (APT) detection techniques in big data multimedia analytics
• Machine learning algorithms for effective detection of cyber-attacks with big data multimedia analytics
• Representation of cyber-attack data for cross-platform processing
• Network forensics using big data analytics
• Stream data processing for real-time threat analysis
• Zero-day attack detection using big data analytics
• Big data technology for multimedia indexing and retrieval
• Secure big data technology for multimedia analytics
• Scientific programming for multimedia data processing