Training Description
Key Takeaways
- Focuses on AI safety and security in mission-critical sectors
- Bridges dependability and AI research communities
- Covers technical, regulatory, and ethical challenges in AI adoption
- Features interdisciplinary collaboration and thought leadership
- Targets researchers, practitioners, and professionals in AI and cybersecurity
The 1st International Workshop on AI Safety and Security (AI-SS 2026) is a pioneering event dedicated to addressing the risks and uncertainties introduced by Artificial Intelligence in safety- and mission-critical domains. This workshop brings together experts from diverse backgrounds to foster collaboration and advance the state of AI safety, security, and trustworthiness. Co-located with the 21st European Dependable Computing Conference, the event provides a unique platform for exchanging ideas and developing solutions for dependable and trustworthy intelligent systems.
Event Overview
AI-SS 2026 is designed to bridge the gap between the dependability and AI research communities. The workshop encourages interdisciplinary dialogue, enabling participants to tackle both fundamental and practical challenges in AI safety and security. Attendees will engage in discussions on methodologies, standards, and regulatory frameworks that support the safe and secure integration of AI into critical systems.
The event features a technical and research-focused agenda, including workshops, panel sessions, and paper presentations. It offers opportunities for networking and knowledge exchange among established and emerging researchers, industry professionals, and regulatory experts.
Main Topics and Themes
Key topics include AI safety, reliability, and assurance, secure and resilient machine learning, LLM safety and privacy, adversarial robustness, and AI-driven cybersecurity risk analysis. The workshop also explores formal verification of AI models, trustworthy AI in safety-critical systems, human–AI interaction safety, and the legal, regulatory, and ethical aspects of AI deployment.
Additional areas of focus are federated learning, privacy-preserving AI, incident analysis, failure recovery, and the development of new benchmarks for AI safety and security. These themes reflect the event’s commitment to advancing the dependability and trustworthiness of intelligent systems in critical sectors.
Audience and Participation
The workshop is tailored for researchers, practitioners, and professionals in AI, cybersecurity, and dependability. Likely participants include academics, industry researchers, engineers, cybersecurity specialists, and regulatory experts, particularly those working in critical infrastructure sectors such as healthcare, transportation, energy, nuclear, and finance.
AI-SS 2026 supports education, thought leadership, and community building, while also providing opportunities for lead generation and recruitment, especially for young researchers. The event is supported by leading organizations and features technologies such as AI, machine learning, LLMs, federated learning, and privacy-preserving AI.