Explainable Artificial Intelligence for Security and Privacy in Recommender Systems
摘要截稿:
全文截稿: 2024-07-31
影响因子: 5.91
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 1区
• 小类 : 计算机:信息系统 - 1区
Overview
Recommender Systems (RS) have become one of the most effective approaches to quickly extract insightful information from big data and are not widely applied to various fields such as Smart Healthcare, E-commerce, Intelligent Tourism, Smart Transportation, etc. The characteristics of big data, such as multi-source property and data diversity, require that a recommender system can quickly integrate the data distributed across multiple parties so as to make comprehensive and accurate recommendation decisions. In particular, to protect business secrets and obey laws, securing user data and preserving user privacy during the abovementioned data integration process are very important but challenging requirements in practice.
Machine learning powered Artificial Intelligence (AI) has recently emerged as one of the key technologies to realize multi-source data analyses and knowledge utilization. Therefore, AI has provided a promising way to achieve the abovementioned security and privacy goals in RS. However, current AI-based security and privacy research in RS still falls short in providing a good explanation of how the AI algorithms or models can balance a series of conflicting recommendation criteria well, e.g., security, accuracy, robustness, privacy, efficiency, etc. Therefore, the adaptation of explainable AI models and technologies is highly demanded to achieve their full potentials in guaranteeing user security and privacy in RS.
This special issue focuses on the challenges and problems in Explainable Artificial Intelligence for Security and Privacy in Recommender Systems. It aims to share and discuss recent advances and future trends of secure, privacy-preserving and explainable AI for RS, and to bring academic researchers and industry developers together.
Guest editors:
Prof. Jinjun Chen (Executive Guest Editor)
Swinburne University of Technology, Australia
Email: jinjun.chen@gmail.com
Prof. Lianyong Qi
China University of Petroleum (East China), China
Email: lianyongqi@gmail.com
Dr. Hayford Perry Fordson
Cornell University, USA
Email: perryfordson@cornell.edu
Special issue information:
The topics of interest include, but are not limited to:
Empirical studies of secure and explainable AI for RS
Explainability of AI models/algorithms in dependable RS
Explainable AI for Privacy techniques/protocols in RS
Adversarial attack and defense in RS with explainable AI
Blockchain-based security solutions for RS with explainable AI
Authentication and Anonymity for explainable AI-based RS
Novel explainable AI techniques or applications to distributed RS
Explainable AI to detect potential biases for secure RS
Novel evaluation frameworks of explainable AI for RS
Explainability of federated learning for cross-platform RS
Lightweight security and privacy solutions with explainable AI for RS