AI and Federated Learning for secure Information Processing and Applications

in Special Issue   Posted on May 27, 2021 

Information for the Special Issue

Special Issue Call for Papers:

Rationale

Today, AI technology is showing its strengths in almost every industry and most walks of life. We have indeed witnessed the huge potential in AI and have begun to expect more complex, cutting-edge AI technology in many applications, including driverless cars, medical care, and finance. The current success in AI is partly driven by Big Data availability. Traditional data-processing models in AI often involve simple data transaction models. One party collects and transfers data to another party and the other party is responsible for cleaning and fusing the data. Finally, a third party will take the integrated data and build models for other parties. The models are usually the final products that are sold as a service. However, the emphasis on data privacy and security has become a major worldwide issue. This traditional procedure faces challenges with the new data regulations and laws, such as the General Data Protection Regulation (GDPR). As a result, we face a dilemma that our data is in the form of isolated islands. Still, we are forbidden in many situations to collect, fuse, and use the data in different places for AI processing. How to legally solve data fragmentation and isolation is a major challenge for AI researchers and practitioners today.

The isolation of data and the emphasis on data privacy became the next challenges for AI, but federated learning has brought us new hope. The concept of federated learning was proposed by Google recently to build machine-learning models based on datasets that are distributed across multiple devices while preventing data leakage. Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Recent improvements have been focusing on overcoming the statistical challenges and improving security in federated learning. There are also research efforts to make federated learning to be a general concept for all privacy-preserving decentralized collaborative machine-learning techniques. It is expected that, in the near future, federated learning would break the barriers between industries and establish a community where data and knowledge could be shared with safety and the benefits would be fairly distributed according to the contribution of each participant. The bonus of AI would finally be brought to every corner of our lives.

This special issue provides an in-depth overview of artificial intelligence and deep learning-based secure information processing approaches with case studies to solve problems associated with cybersecurity such as authentication, indexing, template protection, spoofing attack detection, crime scene investigation, forensics in multimedia data, intrusion detection, gender classification etc. In this special issue, we are looking for cutting-edge technologies, novel studies, and promising developments, which can realize and elevate the effectiveness and advantages of secure Information Processing for critical infrastructure protection.

Potential topics include but are not limited to:
o Authentication and authorization based on AI and federated learning
o Processing multimedia protection for data confidentially based on AI and deep learning
o Information hiding –based AI mechanism s for data protection
o Blockchain-based federated learning protocol
o Deep learning for Image/Video Forensics
o Deep learning-based anti-forensics
o Deep learning for multimedia security
o Deep learning for cyber security applications (e.g., malicious web content identification, intrusion detection and privacy-preserving, vulnerability and exploitation Identification, and facial and/or biometric spoofing detection)
o AI-Driven Communications and Networks
o Big Data Networking and Applications
o Blockchain and Distributed Ledger Technologies
o Consumer Communications and Networking
o AI and federated learning-based Cyber-Physical Systems
o AI and federated learning-based Edge, Fog, and Cloud Computing and Networks
o AI and federated learning-based Green Communications
o AI and federated learning-based Industrial Internet and Industry 4.0
o Intelligent Communications and Networking Systems
o Optical Communications and Networking
o Pervasive Computing and Networking
AI and federated learning-based Quantum Computing, Communications, and Information
o Satellite Communications and Networking in Space
o Trust, Security, and Privacy Protocols
o AI and federated learning-based Vehicular Communications and Networks
o AI and federated learning-based Wireless Sensor Networks

Schedule
Paper Submission: 15 December 2021
Revision/Acceptance Notification: 15 January2021
Revised Manuscript Due: 15 February 2022
Final Decision Notification: 15 March 2022
Publication: As per EIC’s choice

Guest Editors:

Prof. Ahmed A. Abd El-Latif, Associate Professor, Menoufia University, Egypt, Email: [email protected]

Prof. Francesco Piccialli, Department of Mathematics and Applications \”R. Caccioppoli\”, University of Naples Federico II, Email: [email protected]

Prof. Shahid Mumtaz, Instituto de Telecomunicações, Campus Universitário de Santiago, 3810-193 Aveiro, Portugal, E-mail: [email protected]

Prof. Chang Choi, Assistant Professor, Gachon University, South Korea, Email: changchoi[email protected]

Prof. Yassine Maleh, IEEE Senior Member, Associate Professor, University Sultan Moulay Slimane, Morocco. Email: [email protected]

Prof. Cristina Alcaraz, Associate professor at the Computer Science Department of the University of Malaga (UMA), Spain, Email: [email protected]

Other Special Issues on this journal

Closed Special Issues