The fusion of scalable computing infrastructure, big data, and artificial intelligence (including large language models and multi-agent systems) has boosted the development and application of data science and advanced data analytics. However, emerging threats to the private, secure, and trustworthy (PST) data and analytics models have risen dramatically with the widespread deployment of data analytics applications.

This special session mainly focuses on privacy, security, and trust challenges in data analytics, covering (but not limited to) the following topics: privacy-preserving technology, privacy attacks, federated learning, machine unlearning, data poisoning attacks, model evasion attacks, adversarial learning, model robustness, large language model and multi-agent security, secure machine learning integrating cryptographic techniques, IoT data security, blockchain techniques for data and model PST protection, etc. This special session invites authors to submit original research work that demonstrates and explores cutting-edge advances across all the aforementioned related areas. High-quality accepted papers will be recommended to the associated journal special issues (see more details in Call for Papers).