1st International Workshop on AI Safety and Security (AI-SS 2026)

1st International Workshop on AI Safety and Security (AI-SS 2026) aims to bridge the dependability and AI research communities by addressing fundamental and practical challenges in AI safety, security, and trustworthiness.

Key Topics

• Secure and resilient machine learning
• Foundations of AI safety, reliability, and assurance
• Adversarial robustness and mitigation strategies
• LLM safety, security and privacy
• Formal verification and validation of AI models
• AI-driven cyber security risk analysis
• Humanâ€"AI interaction safety and cognitive trust
• Trustworthy AI in safety-critical systems (e.g., autonomous vehicles, nuclear industry, healthcare and finance)
• Ethical, fairness and transparency aspects of AI safety and security
• Legal and regulatory aspects of AI safety and security
• Federated learning and privacy-preserving AI
• AI for dependability enhancement and system resilience
• New datasets and benchmarks for AI safety and security
• AI incident analysis and failure recovery mechanisms
• Comparative studies of AI safety and security

Who should Attend

Attendees involved or interested in:

• Cyber security
• AI
• Dependability
• Safety
• Ethics
• ICT
• Business and Management
• Law