Primary
Safe AI for autonomous systems
Designing frameworks that improve how safety, reliability, and assurance are argued when AI systems operate in high-consequence environments.
01
About
A concise overview of the research direction, strengths, and academic positioning behind the work.
Danial Safaei is a PhD researcher at WMG, University of Warwick, investigating how to make AI systems for autonomous settings more trustworthy, measurable, and deployment-ready.
His work focuses on the parts of modern AI that matter most when systems leave the lab: how systems are tested, how synthetic data should be evaluated before it is trusted, and how safety claims can be made with greater rigor.
That agenda has led to contributions spanning smart environments, biomedical AI, and autonomous-system validation, but the common thread is consistent: building methods that are technically grounded, explainable, and useful in safety-critical practice.
What defines the work
- Methodological rigor over visual novelty or hype.
- Research questions tied to real deployment constraints.
- Clear bridges between theory, evaluation, and practical safety evidence.
02
Research journey
A progression from applied machine learning toward formal, high-stakes validation for autonomous intelligence.
-
2023
-
2024
-
2025
-
Now
Safe AI for autonomous systems
Ongoing work continues within Safe AI for autonomous systems, building on the evaluation and fidelity methods developed above.
03
Research focus
Connected areas of interest across trustworthy AI and autonomous systems.
Testing
Scenario-based testing
Testing autonomous systems against the conditions that matter most for safety and reliability.
Validation
Synthetic data fidelity
Measuring whether synthetic data is not merely realistic in appearance, but faithful to the underlying decision-relevant structure seen in real data.
04
Selected publications
Representative outputs across safe AI, computer vision, and graph-based learning.
Quantifying Fidelity: A Decisive Feature Approach to Comparing Synthetic and Real Imagery
Introduces the DFF framework, an interpretable method for assessing whether synthetic images preserve the decision-relevant features that real-world performance depends on.
DeePLT: Personalized Lighting Facilitated by Trajectory Prediction of Recognized Residents in Smart Home
A deep-learning framework for adaptive smart-home lighting informed by resident trajectory prediction, published in the International Journal of Information Technology.
GraphSAGE Discovers Synergistic Combinations of Gefitinib, Paclitaxel, and Icotinib for Lung Adenocarcinoma Management
Uses graph neural networks to identify drug synergy in lung adenocarcinoma, demonstrating methodology transfer to clinically significant biomedical problems.
05
Open research code
Code that supports reproducibility, transparency, and practical access to the research.
Featured repository
Decisive Feature Fidelity (DFF)
Reference implementation for the DFF framework, supporting transparent evaluation of fidelity between synthetic and real imagery.
Website source
danial-safaei.github.io
This site is intentionally lightweight: a static portfolio built with plain HTML, CSS, and JavaScript for fast loading and easy maintenance.
Full catalogue
All public repositories
Browse the wider body of public work, experiments, and supporting research artefacts on GitHub.
06
Contact
For research collaboration, speaking opportunities, or technically serious conversations about Safe AI and autonomous-system validation.
If you are working on trustworthy AI, simulation-to-real transfer, validation methodology, or evidence for autonomous-system safety, I would be glad to connect.