Adversarial Robustness and Advanced Security Paradigms in Artificial Intelligence

Dear Colleagues,

The rapid proliferation of Artificial Intelligence (AI) across mission-critical domains has heightened the urgency for rigorous, systemic security frameworks. While modern machine learning models offer transformative capabilities, they remain inherently vulnerable to sophisticated exploitation. This Special Issue, “Adversarial Robustness and Advanced Security Paradigms in Artificial Intelligence”, focuses on the critical intersection of machine learning vulnerability analysis and defensive engineering.

Traditional cybersecurity measures often fail to protect neural networks from domain-specific threats. Consequently, this issue seeks to explore advanced paradigms capable of guaranteeing structural, data, and algorithmic integrity. We welcome high-quality, original research addressing fundamental challenges in adversarial machine learning, including evasion and poisoning mitigations, certified robustness, and privacy-preserving computation. Additionally, we encourage submissions investigating novel threat modeling, secure MLOps, and zero-trust architectures tailored for intelligent systems. By bridging the gap between theoretical vulnerability and resilient deployment, this collection aims to define the next generation of secure, battle-tested AI systems capable of defying adversarial manipulation in real-world environments.

This Special Issue serves as a premier venue for presenting novel architectures, theoretical advancements, and empirical evaluations that reinforce the security posture of AI/ML ecosystems. Submissions are expected to address deep technical vulnerabilities or present comprehensive architectural paradigms. The detailed scope is organized into the following core technical areas: adversarial vulnerability and defense verification; data and structural integrity; advanced cryptographic and privacy paradigms; decentralized and federated AI security; generative AI and LLM security; and enterprise security architecture for AI.

Dr. Muhammad Zeeshan Baig
Dr. Zulfiqar Ali
Dr. Muhammad Imran
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. Machine Learning and Knowledge Extraction 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.