Robustness and Security in Machine Learning Systems
A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".
Deadline for manuscript submissions: 15 November 2026
Special Issue Editors
Interests: distributed and decentralized optimization; edge computing
Interests: security and privacy in UAV networks; LLM-empowered agents
Special Issues, Collections and Topics in MDPI journals
Interests: resource management; quantum annealing; machine learning; the Internet of Things
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
The track on robustness, interpretability, and security in machine learning systems invites original contributions on the design, analysis, and deployment of trustworthy machine learning methods and systems. As machine learning is increasingly adopted in mission-critical, privacy-sensitive, and safety-relevant applications, it is essential to ensure that such systems remain reliable under distribution shifts, adversarial manipulation, noisy observations, limited resources, and dynamic operating conditions. This Special Issue seeks research that advances principled understanding and practical solutions for improving model robustness, enhancing interpretability and transparency, and strengthening security and privacy guarantees throughout the learning lifecycle. Topics of interest include theoretical foundations, algorithmic innovations, system architectures, benchmarking methodologies, and real-world applications involving trustworthy ML, foundation models, federated learning, edge intelligence, autonomous systems, and cyber–physical platforms. Contributions that bridge machine learning with optimization, control, cryptography, formal methods, human-centered AI, and systems engineering are especially encouraged. The goal of this track is to foster advances in machine learning systems that are not only accurate and efficient, but also resilient, explainable, secure, and dependable in practice.
Topics of Interest
- Adversarial machine learning and Byzantine robustness;
- Privacy-preserving learning, e.g., differential privacy and secure aggregation;
- Fine-tuning methods of large language models and multimodal foundation models;
- Out-of-distribution detection and domain generalization;
- Explainable AI and interpretable model design;
- Security and privacy in training and inference;
- Data poisoning, backdoor attacks, and defense mechanisms;
- Membership inference, model inversion, and model stealing attacks.
Dr. Yanjie Dong
Dr. Yuntao Wang
Dr. Aohan Li
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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics 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 2400 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
- adversarial machine learning
- byzantine robust machine learning
- fine-tuning methods of LLMs
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.
