Call for Papers: Security and Privacy for Intelligent Multimedia Processing in the Era of Big Data 
With the proliferation of mobile communication technology and the booming of smart devices, a significant amount of multimedia big data has been generated, transmitted, stored and processed, which forms multimedia big data of diverse formats (such as videos, animations, audios, images, texts). Since multimedia documents are naturally unstructured and generated from multiple models, real-time and high-resolution manipulation requirements impose a great challenge to multimedia processing. Recently artificial intelligence (AI) driven big data processing techniques are exploring to handle large-scale heterogeneous multimedia data. The intelligent multimedia big data processing, based on machine learning, neural network, deep learning and pattern recognition, enables moving target detection, automatic speech recognition, medical diagnosis, financial data analysis, and fault diagnosis to facilitate.
Although bringing AI into big data processing could comprehensively enhance service quality, the issues of security, privacy and trust remain a challenge due to the high possibility of a data breach during the multimedia compression, transmission and analysis. The machine learning-based intelligent system resorts a training algorithm on multimedia data to fulfil the classification, recognition, or decision tasks. It is necessary to ensure privacy protection on the training multimedia data and the trained model parameters. On the other aspect, large-scale or distributed multimedia big data processing consumes large computation and storage resources, which are usually outsourced to cloud platforms. Since many machine learning or deep learning-based models are vulnerable to various attacks, such adversarial inputs, data poisoning attacks, evasion attacks, outsourcing multimedia and intelligent big data processing algorithms should guarantee the confidentiality, integrity and auditability of the training multimedia. The stylish, secure computation methods (such as multi-party computation, differential privacy, homomorphic encryption, garbled circuit) can be considered for the outsourced multimedia big data processing with the balance of efficiency, security and accuracy. Besides, the traditional privacy protection solutions for multimedia processing should be evolved by up-to-date AI technologies.
The goal of this special issue is to collect high-quality theoretical and applied contributions in topics including, but not limited to:
- Innovative techniques using AI for security, privacy and trust frameworks in the multimedia big data processing
- Secure distributed and decentralized intelligent multimedia big data processing
- Machine learning-based secure, intelligent multimedia big data processing
- Models and algorithms for the security and privacy of multimedia big data processing
- Scalability issues of secure multimedia computing
- Privacy-preserving information retrieval and intelligent decision support systems for multimedia big data processing
- Encryption, signature and forensics for securing multimedia big data processing
- Secure infrastructures of acquisition, storage, and transmission for multimedia big-data
- Trust, privacy and security issues in the outsourced intelligent multimedia big data processing
- Secure AI-based network resource allocation and optimization for multimedia big data processing
- Privacy-preserving analytic and predictive models for multimedia big data processing
- Security and privacy for the convergence of big multimedia data
- Secure optimization, control, and automation for multimedia big data processing
- Node/user privacy in intelligent multimedia big data processing
- Secure and efficient hardware, devices, and designs for intelligent multimedia big data processing
- Privacy-preserving machine learning and deep learning in industrial-level multimedia big data process and control
Dr. Hui Cui
Murdoch University, Australia
Prof. Hung-Min Sun
National Tsing Hua University, Taiwan
Deadline for submission: extended to January 15, 2021
First review notification: March 15, 2021
Revision submission: April 30, 2021
Second review notification: June 15, 2021
Final notification to authors: July 31, 2021
Publication (expected): Autumn or winter 2021
Authors should prepare their manuscript according to the Instructions for Authors available from the Multimedia Tools and Applications website. Authors should submit through the online submission site at https://www.editorialmanager.com/mtap/default.aspx and select “SI 1184 - Security and Privacy for Intelligent Multimedia Processing in the Era of Big Data” when they reach the “Article Type” step in the submission process. Submitted papers should present original, unpublished work, relevant to one of the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process.
The special issue will consider papers extending previously published conference papers, provided the journal submission presents a significant contribution beyond the conference paper. Authors must explain in the introduction to the paper the new contribution to the field made by the submission, and the original conference publication should be cited in the text. Note that neither verbatim transfer of large parts of the conference paper nor wholesale reproduction of already published figures is acceptable.