Topics of Interest

The Workshop welcomes submissions covering one or more of the following topics (including but not limited to):

• Foundations of AI safety, reliability, and assurance
• Secure and resilient machine learning
• LLM safety, security and privacy
• Adversarial robustness and mitigation strategies
• AI-driven cyber security risk analysis
• Formal verification and validation of AI models
• Trustworthy AI in safety-critical systems (e.g., autonomous vehicles, nuclear industry, healthcare and finance)
• Human–AI interaction safety and cognitive trust
• Legal and regulatory aspects of AI safety and security
• Ethical, fairness and transparency aspects of AI safety and security
• AI for dependability enhancement and system resilience
• Federated learning and privacy-preserving AI
• AI incident analysis and failure recovery mechanisms
• New datasets and benchmarks for AI safety and security
• Comparative studies of AI safety and security

Submission Instructions

Submissions should be made through the Workshop's paper submission system on the Microsoft CMT (Conference Management Toolkit) service.

All submissions must be written in English and adhere to the camera-ready two-column format of IEEE Computer Society. Submissions should have maximum 8 pages (everything included) and must be submitted as a single PDF file. Templates and guidelines from IEEE can be found here.

A paper submitted to AI-SS 2026 cannot be under review at any other venue - including conferences, workshops, journals and book chapters - during the entire period when the paper is being considered by this Workshop. Furthermore, after a paper is submitted to AI-SS 2026, the authors must await the result and only then resubmit elsewhere if the paper is rejected (or withdrawn at their request) from this Workshop. All papers submitted to AI-SS 2026 must present substantial new content not described in any prior publication that is formally published. If a submission overlaps with a prior publication, the submission must cite the prior publication and clearly explain the relationship between the two.

Publicly disclosed research in the form of preprints (e.g., on arXiv.org, the authors' own websites or their institutions' repositories) that have not been peer reviewed or published formally are permitted to submit to AI-SS 2026. Academic misconducts such as plagiarism including self-plagiarism are not permitted.

Submissions that violate any of the above rules, are off-topic, or are not formatted correctly will be desk rejected without review.

Submissions will undergo a single-blind review process. Authors are allowed to include their names and affiliations in the submitted manuscript. We aim to allocate three reviewers to each submitted manuscript and the reviewers will be mainly members of the technical program committee (TPC), but additional reviewers with relevant expertise may also be involved.

Accepted papers will be included in a companion proceedings of EDCC 2026, which will be published by the Conference Publishing Services (CPS) and be submitted for possible publication in IEEE Xplore.

At least one author of each accepted paper must register via the EDCC 2026 conference website and present the paper at AI-SS 2026.

Best Paper Award and Best Student Paper Award

The Organising Committee of AI-SS 2026 will select one accepted paper to receive a Best Paper Award and a paper whose first author is a student to receive a Best Student Paper Award. Each award will come with a certificate and a cash prize sponsored by the Institute of Cyber Security for Society (iCSS), University of Kent, UK.

CMT Acknowledgment

The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.