Generative Artificial Intelligence and Privacy-Preserving Machine Learning

Dear Colleagues,

The rapid ascent of Generative Artificial Intelligence (GenAI) has unlocked unprecedented capabilities in creating realistic synthetic data, powerful large language models, and innovative content. However, this power raises critical concerns over privacy, security, and ethical governance. GenAI models are prone to memorizing and potentially leaking sensitive information from their training data through various attacks, such as membership inference and model inversion.

This Special Issue will explore the vital intersection of Generative AI and Privacy-Preserving Machine Learning (PPML). It aims to investigate how PPML techniques can be leveraged to build responsible, trustworthy, and ethical GenAI systems that mitigate privacy risks. Conversely, it will also examine how GenAI itself can be used as a tool to enhance privacy, for example, through the generation of high-quality synthetic datasets that preserve statistical utility without exposing real individual records.

We seek to bring together researchers and practitioners to present original research and review articles that address the theoretical, practical, and ethical challenges at this crossroads. This issue will serve as a platform for the dissemination of cutting-edge solutions that ensure that the next generation of AI innovations is both powerful and privacy-conscious.

Topics of interest include, but are not limited to, the following:

• Privacy risks in Generative AI (e.g., membership inference, reconstruction attacks);
• Differential privacy for training and deploying Generative AI models (GANs, VAEs, Diffusion Models, LLMs);
• Federated Learning for decentralized training of GenAI models;
• Synthetic data generation for privacy protection and data sharing;
• Homomorphic encryption and secure multi-party computation for secure GenAI inference;
• Verifiable and transparent GenAI to ensure accountability;
• Fairness, bias, and ethical implications of privacy-preserving GenAI;
• Regulatory compliance (GDPR, HIPAA) and standards for GenAI;
• Applications in healthcare, finance, IoT, and biometrics;
• Benchmarks and evaluation metrics for privacy-utility trade-offs in GenAI.

Dr. Anurag Bhardwaj
Guest Editor

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. Computers is an international peer-reviewed open access monthly 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 1800 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.