Aim and Scope

Data intelligence and data security are two closely related areas. In the era of big data, both data intelligence and data security are very important, and present constant challenges for both academia and industry. Those challenges bring with great opportunities for innovative ideas, tools and technologies.

The 4th International Conference on Data Intelligence and Security (ICDIS-2022) aims to:

(1) provide a unique forum where data intelligence and data security are all involved;

(2) provide a forum for researchers, experts, professionals and stakeholders in related fields to disseminate their recent advances and share their views on future perspectives.

Themes

The topics of ICDIS-2022 include two aspects. First, contributions on data intelligence in security and privacy are welcome, including works on how to learn from data and how to intelligently process data for security and privacy applications. Second, contributions on security and privacy in data intelligence are always within the scope of the conference, including works on making data intelligence models secure and trusted.

Particularly, the topics of interest include but are not limited to:

Topic 1: Data Intelligence in Security and Privacy
​
Intrusion detection
Anomaly detection
Fraud detection
Defense against Malicious codes
Defense against denial of service attacks
Network security
System security
Biometrics
Deep learning
Unsupervised learning and clustering
Supervised learning and classification
Reinforcement learning
Data mining
Robust and dynamic optimization
Visualization and analysis
Immune computation

Topic 2: Security and Privacy in Data Intelligence
​
Federated learning
Swarm learning
Poisoning attack and defense
Evasion attacks and defense
Adversarial examples
Model inversion
AI backdoors
Membership inference attacks
Digital watermarking for AI models
Privacy-preserving machine learning
Privacy-preserving data mining
Privacy-preserving data publishing
Secure model processing platforms
Security and privacy in social networks
Interpretability of machine learning models for secure machine learning
Secure machine learning
Secure cloud computing
Secure multi-party computation
Data privacy
Sensitive data collection
AI fairness
AI trust
AI ethics
Blockchain