Embedded Files
A full day of talks, discussions and interactions to to contribute to shaping the future of AI safety research within the UAI and the broader AI community.
A full day of talks, discussions and interactions to to contribute to shaping the future of AI safety research within the UAI and the broader AI community.
AI safety has been largely recognized in the public sector, healthcare, and across industries, as highlighted by (yet incomplete) EU initiatives and regulations. The workshop will aim at technical and socio-technical challenges of the development and application of AI, including AI value alignment, AI compliance, AI robustness and Human-AI collaborations, with focus on pathways to societal impact in the context of next-generation AI and data intelligence (eco)systems. There is no room for safe AI without a proper treatment of uncertainty, including measurements, theoretical analyses, and decision making.
Topics of Interest
Topics of Interest
The workshop will foster technical discussions on cutting-edge safety techniques, including uncertainty quantification, adversarial robustness, and socio-technical discussions including AI alignment with human values, fairness and non-crimination among other important topics.
Broadly, the workshop aims at discussing any techniques/topics that facilitate design and development of the Future-Proof AI including but not limited to...
Broadly, the workshop aims at discussing any techniques/topics that facilitate design and development of the Future-Proof AI including but not limited to...
Foundations and different learning settings
Uncertainty modelling and treatment for safe AI
AI Robustness and Reliability
LLMs and AI agents hijacking and defense mechanisms
Safe Reinforcement Learning
Safe Federated Learning
Safe Frugal AI
Safety in Human-in-the-loop approaches
Methods to audit, measure, and evaluate AI safety
Auditing methods and tools
Benchmarks and case studies
Standard and best practices
Explainability, traceability, data and model lineage
Visual analytics and HCI for understanding/auditing AI for safety aspects
Software engineering (design and testing) approaches
Applications
AI in Safety-Critical Systems
SafeAI for Peace
SafeAI in Healthcare
SafeAI in Cybersecurity
SafeAI in Education
SafeAI in Manufacturing
SafeAI in Autonomous systems
Safe resource allocation
Please refer to the Call for Papers to contribute to the program of the workshop.
Keynotes
Keynotes
Contributes talks
Contributes talks
Panel discussions
Panel discussions
Important Dates
Important Dates
EXTENDED DEADLINE
Paper submission deadline: 30 May 2025 13 June 2025
Reviewing period: 1-16 June 2025 1-17 June 2025
Paper author notification: 18 June 2025
Camera ready deadline: 1 July 2025
Program and papers available online: 10 July 2025
The venue is the same as for the main conference - the Rio Othon Palace Hotel. It offers special rates for the SafeAI / UAI attendees by using the promotional code: UAI2025.
Page updated
Google Sites
Report abuse