Privacy-Preserving Machine Learning in Large Language Models (LLMs)
A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".
Deadline for manuscript submissions: 1 July 2025 | Viewed by 2116
Special Issue Editors
Interests: blockchain; cryptography; cloud computing; privacy-preserving
Special Issues, Collections and Topics in MDPI journals
Interests: cloud data security and privacy protection; mobile data security; big data security
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
In recent years, the field of artificial intelligence has witnessed significant advancements, notably in the development of Large Language Models (LLMs) like GPT, BERT, and others. These models, powered by extensive datasets and complex neural network architectures, have shown remarkable capabilities in generating human-like text, understanding context, and even performing sophisticated reasoning tasks. However, the rapid adoption and integration of LLMs across various sectors raise substantial concerns regarding data privacy and security.
The proposed Special Issue will focus on “Privacy-Preserving Machine Learning in Large Language Models (LLMs)”, aiming to spotlight innovative research, methodologies, and technologies that ensure privacy and security in the training and application phases of LLMs. It will cover theoretical advancements, practical implementations, and regulatory considerations that address how data used in LLMs can be protected against unauthorized access and misuse.
This Special Issue welcomes original research articles, review papers, case studies, and short communications on topics including, but not limited to, the following:
- Techniques for anonymizing data used in training LLMs;
- Federated learning approaches for decentralized model training;
- Differential privacy techniques and their application in LLMs;
- Secure multi-party computation (SMPC) solutions for LLMs;
- Homomorphic encryption methods for privacy-preserving computations in LLMs;
- Assessment of privacy risks and vulnerabilities in existing LLM frameworks;
- Policy and regulatory frameworks for privacy in AI and machine learning;
- Case studies on the implementation of privacy-preserving mechanisms in LLMs;
- Ethical implications of data privacy in LLMs;
- Mathematic foundations for explainable LLMs;
- Machine Unlearning and its application in LLMs.
Dr. Zuobin Ying
Prof. Dr. Jinbo Xiong
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 100 words) can be sent to the Editorial Office for announcement on this website.
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-blind 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.
Keywords
- privacy preserving
- large language models
- machine unlearning
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
