International Workshop on AI Reliability and Security (AIRS 2025)

Description

Artificial Intelligence (AI) algorithms, models, agents and systems have witnessed a remarkable proliferation across diverse domains, encompassing image and speech recognition, machine translation, natural/programming language understanding, and intrusion detection, among others. The advent of AI has revolutionized these fields, enabling unprecedented advancements and transformative capabilities. However, the very essence of AI, characterized by its intelligent nature and the ability to learn and adapt, introduces novel failure modes that distinguish it from traditional software. These unique failure modes arise due to the inherent complexity and non-linearity of AI systems, making their reliability a critical concern. Ensuring the trustworthiness, correctness, and dependability of AI systems has emerged as a pressing challenge that demands immediate attention.

This workshop aims to foster discussions, share recent developments, and address the current challenges in improving the reliability of AI algorithms/models/agents/systems. It provides a platform for researchers and practitioners to exchange their research findings, experiences, and insights.

Topics

The list of topics includes, but is not limited to:

• Techniques and methodologies for testing and validating AI algorithms/models/agents/systems
• Reliability analysis and assurance for AI algorithms/models/agents/systems
• Security challenges and solutions in AI algorithms/models/agents/systems
• Explainability and interpretability of AI models for improved reliability
• Robustness and resilience of AI systems in the face of adversarial attacks
• Verification and validation of AI-driven systems in safety-critical applications
• Case studies, best practices, and lessons learned in AI reliability and security

Submission

Authors are invited to submit original unpublished research papers as well as industrial practice papers. Simultaneous submissions to other conferences are not permitted. Detailed instructions for electronic paper submission, panel proposals, and review process can be found at QRS submission.

Each submission can have a maximum of ten pages. It should include a title, the name and affiliation of each author, a 300-word abstract, and up to 6 keywords. Shorter version papers (up to six pages) are also allowed.

All papers must conform to the QRS conference proceedings format (PDF | Word DOCX | Latex) and Submission Guideline set in advance by QRS 2025. At least one of the authors of each accepted paper is required to pay the full registration fee and present the paper at the workshop. Submissions must be in PDF format and uploaded to the conference submission site. Arrangements are being made to publish extended version of top-quality papers in selected SCI journals.

Program Chairs

Junjie Wang

Chinese Academy of Sciences, China

Weisong Sun

Nanyang Technological University, Singapore

Program Committee