Engineering Safety-Critical AI Systems
AAAI Symposium 2025 • Building AI Systems for Safety-Critical Applications
Duration
2.5 Days
Format
Keynotes, Papers & Panels
Submission Deadline
August 11, 2025
Notification
August 22, 2025
About the Symposium
Artificial intelligence has increasing application to high-risk settings, but foundational practices for engineering safe AI systems remain few, and research in safety engineering for AI remains scattered across disparate fields of study.
This symposium strikes at a fundamental question: How should we build AI systems for safety-critical applications?
We bring together three communities: domain experts who want to use AI in safety-critical applications, AI researchers and practitioners who build AI capabilities, and safety and systems engineers who design, develop, and test systems that include AI components.
Important Dates
Submission Deadline
All papers must be submitted through AAAI EasyChair by 11:59 PM UTC
Notification
Authors will be notified of acceptance or rejection decisions
Camera-Ready
Final versions of accepted papers due for proceedings
Topics of Interest
While most topics around safety and AI are welcome, we are especially interested in topics that inform how to engineer AI systems now and in the future:
Safety Requirements Engineering
Safety requirements engineering for AI and/or new safety standards for AI systems
Software Architectures
Software architectures for increased AI system safety
Uncertainty & Robustness
Uncertainty quantification and/or robustness in AI components or systems
System Specifications
Methods for defining AI system specifications
Testing & Evaluation
Safety test and evaluation of AI components or systems
Safety Tooling
Software tooling to support safety engineering in AI
Failure Analysis
Reporting of high impact failure modes or cases in AI systems
Domain Applications
High-risk application domains of AI that require specific definitions of safety
Case Studies
Case studies of safety engineering for deployed AI systems
Formal Verification
Formal specification and verification of AI systems and/or processes for certifying AI system safety
Safe-by-Design AI
Provably safe AI and safe-by-design AI approaches
Human-AI Interaction
Human-AI interaction in safety-critical systems
Submission Tracks
1Research and Development
This track seeks papers articulating new AI safety research or technical reports describing new safety engineering artifacts (process, procedure, standards, software architectures, tooling, etc.).
Preference will be given to works that are:
- Rigorous and well-evidenced
- Have evidence to support real-world application
- Advance the discipline of engineering safe AI systems
2Case Studies in Engineering AI Systems
This track seeks papers that highlight the practical engineering challenges with building safe AI systems in a challenging application domain and/or present a case study in engineering safe AI systems in the real world.
Preference will be given to works that:
- Showcase real-world problems with high impact
- Present rigorous and well-justified engineering solutions
Submission Requirements
Paper Formats
- Short papers: 2-4 pages (excluding references)
- Full papers: 6-8 pages (excluding references)
Submission Details
- Use AAAI-25 author kit formatting
- Submit through AAAI EasyChair site
- Single-blind review (papers not anonymized)