Special Issue on Security and Privacy in Machine Learning
摘要截稿:
全文截稿: 2018-07-15
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
Machine learning has been widely applied in many important fields such as health monitoring, decision making, image processing, and financial predictions etc. To obtain more accurate classifier, sufficient training data from a set of data owners are necessary for appropriate learning algorithms. However, a dataset usually contains sensitive information of data owner in most applications, which creates a certain barrier for sharing the data among data owners for machine learning tasks. Protecting data privacy in machine learning is complex and difficult, since the mechanism should enable to perform learning over the dataset meanwhile preserve data privacy. Moreover, due to computation and storage bottlenecks, data storage and learning computation have to be outsourced to cloud servers rather than executed locally, and the cloud computing also makes the problem of privacy leakage more visible. As a result, there is an increasing demand for the development of new security and privacy approaches to guarantee the security, privacy, and availability of data in machine learning.
This feature topic will benefit the research community towards identifying challenges and disseminating the latest methodologies and solutions to security and privacy issues in machine learning. The ultimate objective is to publish high-quality articles presenting open issues, delivering algorithms, protocols, frameworks, and solutions for machine learning related to security and privacy. All received submissions will be sent out for peer review by at least three experts in the field and evaluated with respect to relevance to the special issue, level of innovation, depth of contributions, and quality of presentation. Case studies, which address state-of-art research and state-of-practice industry experiences, are also welcomed. Guest editors will make an initial determination of the suitability and scope of all submissions. Papers that either lack originality, clarity in presentation or fall outside the scope of the special issue will not be sent for review and the authors will be promptly notified in such cases. Submitted papers must not be under consideration by any other journal or publication.
Topics of interest include, but are not limited to, the following:
- Privacy-preserving Learning Algorithm
- Privacy-preserving Classification Algorithm
- Secure Data Management in Machine Learning
- Multi-party Secure Computation Techniques for Machine Learning
- Efficient Outsourced Machine Learning Algorithm
- Privacy-preserving Learning Theory
- Privacy-preserving Deep Learning
- Trusted Mechanism for Machine Learning
- Machine Learning with Differential Privacy
- Adversary Machine Learning
- Privacy Standard in Machine Learning Tasks
- Machine Learning Forensics Techniques
- Security & Privacy for Machine Learning Applications
- Light-weighted Secure Machine Learning Techniques in Smart Devices