Topics
The topics of interest for submission include, but are not limited to:
Large Models and Generative AI Security
Prompt Injection and Jailbreak Attacks
Adversarial Examples and Harmful Content Generation
Hallucination Detection and Factual Assurance
Multimodal Model Security
Retrieval-Augmented Generation (RAG) Security
AI Agent Security and Access Control
Tool Calling and External Interaction Security
Red Teaming and Evaluation of Large Language Models
Adversarial Machine Learning and Model Robustness
System components
Virtual reality platform
AI platform for VR/AR
Data and generation, operation, analysis and verification
Generation of immersive environments and virtual worlds
Optimization and realistic rendering
Trustworthy AI and Safety Alignment
Interpretability and auditability
Human feedback alignment risks
Uncertainty estimation and safety decision-making
Goal specification and behavior control
Safety constraint learning
Factuality, consistency, and robustness
Trustworthy assessment and certification
AI safety design for high-risk scenarios
Privacy protection and data security
Training data leakage and inference attacks
Differential privacy and federated privacy
Secure multi-party computation and homomorphic encryption
Privacy leakage of generative models
Data de-identification and compliance governance
Privacy-preserving machine learning
Security of cross-domain data sharing
Privacy evaluation and auditing
AI System and Infrastructure Security
AI Platform and MLOps Security
Model Repository and Supply chain Security
Cloud, Edge and End-Device Deployment Security
Runtime Monitoring and Intrusion Detection
Inference Service and Access Control Security
AI Acceleration Hardware and Firmware Security
Containerization and Microservices Security
Connected Smart Devices and Autonomous Systems Security
AI Safety Governance and Social Impact
AI Safety Standards and Certifications
High-Risk AI Regulation and Auditing
Algorithm Discrimination and Fairness Risks
Misinformation Governance
Safety Ethics and Responsibility Mechanisms
Incident Response and Risk Notification
International Governance and Policy Comparisons
Interdisciplinary Research on AI Safety