Overview
The First Workshop on Resilient AI Framework for Secure and Ethical Machine Learning Systems (RAISE 2025) aims to promote a socio-technical perspective on AI. The workshop focuses on the development of resilient AI systems that uphold human values such as fairness, transparency, privacy, and trust. Resilient AI systems must incorporate robustness, reliability, accountability, and ethical safeguards to adapt effectively to real-world scenarios.
The workshop brings together researchers and practitioners to address challenges including data quality, privacy protection, human-centered AI design, and the validation of machine learning systems. RAISE promotes interdisciplinary discussion to explore innovative techniques and empirical studies for building AI systems that are secure, interpretable, and inclusive.
Topics of interest include, but are not limited to:
- Data profiling approaches for AI systems
- Data quality approaches for AI systems
- Tools and metrics to summarize data relationships
- Privacy concerns of AI systems
- Privacy-preserving machine learning
- Ethics and trustworthy AI
- Reliability and fairness of AI-based systems
- Resilient AI models
- Empirical evaluation of resilient AI solutions in real-world cases
- Verification and validation methods for AI-based systems
- Explainable AI
- AI solutions to critical scenarios
- Domain-specific AI solutions
- AI-based systems for human interaction
- AI-based systems for requirements analysis
- AI-based adaptive systems
- User-centered design solutions for AI-based systems
- AR/VR user-centered interfaces for AI-based systems
- Adaptation of AR/VR in learning contexts
- Neuro-Symbolic AI
Workshop program
Presentations should be 10 minutes long with up to 5 minutes of Q&A
|
Time |
Title/Activity |
|
|
14.00 - 14.15 |
Welcome and Introduction |
|
| Paper Presentations I |
14.15 - 14.30 |
Silvia Torsi, Stefano Bonelli, Anna Giulia Vicario, Alfonso Levantesi and Hossein Mapar
Ambient Light Displays for Situation Awareness in Air Traffic Management |
Session Chair:
Loredana Caruccio |
| 14.30 - 14.45 |
Andrea Terlizzi, Giuseppe Todisco, Francesco Bardozzo and Roberto Tagliaferri
Dynamic Sparse Liquid Time-Constant Networks allow Enhanced Expressivity and Short-Term Memory |
| 14.45 - 15.00 |
Giuseppe Todisco, Andrea Terlizzi, Francesco Bardozzo and Roberto Tagliaferri
Attention Head Diversity Makes Vision Transformers More Noise-Resistant |
| 15.00 - 15.15 |
Simone Cava, Alessandra Parziale, Alfonso Cannavale, Fabio Palomba and Andrea De Lucia
Can Language Models Detect Their Own Bias? An Empirical Study on Prompting for Bias Detection |
| 15.15 - 15.30 |
Grazia Ragone, Paolo Buono and Rosa Lanzilotti
Measuring What Matters: Using AI models to Support Rights-Based Evaluation for Children |
|
15.30 - 16.00 |
Coffee Break |
|
| Paper Presentations II |
16.00 - 16.15 |
Mafalda Ingenito, Otino Pio Santosuosso, Bernardo Breve and Loredana Caruccio
A Cross-Domain Overview of Mixed Reality Object Detection: Technical, Usability, and Ethical Insights |
Session Chair:
Bernardo Breve |
| 16.15 - 16.30 |
Aurelio Sepe, Simone Spera, Andrea Antonio Cantone and Giuliana Vitiello
DomTag: Toward Daily Passive Object Labeling Through Immersive Mixed Reality |
| 16.30 - 16.45 |
Luca Anzalone, Loredana Caruccio, Tullio Pizzuti and Giuseppe Polese
Enhance the interpretation of discovered dependencies through Semantic Header Analysis |
|
16.45 - 17.15 |
Brainstorming and discussion |
|
|
17.15 - 17.30 |
Future directions and wrap up |
|
Submissions
We invite submissions of original research and position papers. Submissions should follow the "1-column CEURART" template:
The minimum length of a CEUR paper should be 5 pages, with approximately 2500 characters (= 380-400 words) per page.
All papers will be reviewed by the organizers and by the program committee based on relevance and significance in order to provide constructive comments to the submitters. Reviewing will be single blind (i.e. author names and affiliations should be listed). If accepted, at least one of the authors must register and attend the workshop.
Submissions should be provided via EasyChair (https://easychair.org/conferences/?conf=raise2025). Accepted papers will be presented at the workshop and included in the CEUR Workshop Proceedings (http://ceur-ws.org/)
Program Committee
| Francesco Bardozzo | University of Salerno |
| Bernardo Breve | University of Naples Federico II |
| Andrea Antonio Cantone | University of Salerno |
| Loredana Caruccio | University of Salerno |
| Giammaria Giordano | University of Salerno |
| Gianpaolo Iuliano | University of Salerno |
| Michele La Rocca | University of Salerno |
| Francesca Perillo | University of Salerno |
| Giuseppe Polese | University of Salerno |
| Gilberto Recupito | University of Salerno |
| Roberto Stanzione | University of Salerno |
| Gianmario Voria | University of Salerno |
