| 10.00-10.15 |
Welcome |
| Session 1 |
Chair: Dr. Carla Di Cairano-Gilfedder (BT) |
 |
|
| 10.15-11.00 |
Guang Yang (Imperial College, London) |
 |
Beyond the Pixel: Trustworthy and Safe Generative AI for Medical Image Quality Transfer |
| 11.00-11.30 |
Prof. Simon Hadfield (University of Surrey) |
 |
Spoofing Deep Leakage Attacks in Federated Learning |
| 11.30-12.00 |
Dr Yunxiao Zhang (Exeter University) |
 |
Can We Trust the Voice on the Line? Robust Audio Deepfake Detection from Real-World Calls to the First “Hi” |
| 12.00-12.15 |
Break |
| 12.15-13.00 |
Ilya Ilyankou (UCL) and James Haworth (UCL) |
 |
The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation |
| 13.00-14.00 |
Lunch Break |
| Session 2 |
Chair: Dr. Carla Di Cairano-Gilfedder (BT) |
|
|
| 14.00-14.30 |
Prof. Simon Hadfield (University of Surrey) |
|
Differential Adjusted Parity for Learning Fair Representations |
| 14.30-15.00 |
Ciaran Bench (National Physical Laboratory) |
 |
Decision-theoretic uncertainty quantification in generative deep learning |
| 15.00-15.15 |
Break |
| 15.15-15.45 |
Ikenna Umeh (BT Research) |
 |
Zero Trust Architectures for Secure Multi-Agent AI Systems: From Identity to Collaboration Integrity |
| 15.45-16.30 |
Panel Discussion / Q&A |
| 16.30 |
Close |
