A Survey on Safe Multi-Modal Learning System

With the wide deployment of multimodal learning systems (MMLS) in real-world scenarios, safety concerns have become increasingly prominent. The absence of systematic research into their safety is a significant barrier to progress in this field. To bridge the gap, we present the first taxonomy for MMLS safety, identifying four essential pillars of these concerns. Leveraging this taxonomy, we conduct in-depth reviews for each pillar, highlighting key limitations based on the current state of development. Finally, we pinpoint unique challenges in MMLS safety and provide potential directions for future research.