New Perspectives in Trustworthiness, Security and Safety of Machine Learning Systems

Dear Colleagues,

As artificial intelligence systems are increasingly deployed in real-world applications such as healthcare, finance, and autonomous driving, ensuring their trustworthiness and security has become a critical concern. Machine learning models, while powerful, are often susceptible to adversarial attacks, data poisoning, privacy breaches, and fairness issues, which may hinder their safe and ethical deployment. Therefore, improving the trustworthiness and security of AI systems is essential for building reliable and responsible intelligent systems.

This Special Issue explores how machine learning methods can be leveraged to enhance the trustworthiness and security of AI systems. We welcome any submissions related to this topic including, but not limited to, the following:

1. Adversarial robustness of machine learning systems;
2. Privacy-preserving machine learning;
3. Fairness of machine learning algorithms;
4. Interpretable and explainable AI models;
5. Data poisoning and model poisoning attacks and defenses;
6. Member inference, attribute inference, and their defenses;
7. Safe reinforcement learning;
8. Robust training under distribution shifts;
9. Noise-robust machine learning methods;
10. Trustworthy federated learning;
11. Security of graph representative learning;
12. Safety of machine learning model deployment;
13. Risk assessment in AI decision-making;
14. Security of large models;
15. Evaluation, detection, and mitigation of large-scale hallucinations;
16. Security of multiple large-model agents;
17. All security and safety aspects of machine learning application systems.

Prof. Dr. Jing Zhang
Dr. Shunmei Meng
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.