In the rapidly evolving landscape of artificial intelligence, multimodal learning systems (MMLS) have gained traction for their ability to process and integrate information from diverse modality inputs. Their expanding use in vital sectors such as healthcare has made safety assurance a critical concern. However, 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 that systematically categorizes and assesses MMLS safety. This taxonomy is structured around four fundamental pillars that are critical to ensuring the safety of MMLS: robustness, alignment, monitoring, and controllability. Leveraging this taxonomy, we review existing methodologies, benchmarks, and the current state of research, while also pinpointing the principal limitations and gaps in knowledge. Finally, we discuss unique challenges in MMLS safety. In illuminating these challenges, we aim to pave the way for future research, proposing potential directions that could lead to significant advancements in the safety protocols of MMLS.

翻译：在人工智能快速发展的背景下，多模态学习系统因其处理与融合多种模态输入信息的能力而备受关注。随着其在医疗等重要领域的广泛应用，安全性保障已成为关键议题。然而，针对其安全性的系统性研究缺失是制约该领域发展的重大障碍。为弥补这一空白，我们首次提出系统分类多模态学习系统安全性的分类体系。该体系围绕确保多模态学习系统安全的四大核心支柱构建：鲁棒性、对齐性、监控性和可控性。依托此分类体系，我们审视了现有方法学、基准测试及研究现状，同时指出了主要局限性与知识空白。最后，我们探讨了多模态学习系统安全领域的独特挑战。通过阐明这些挑战，我们旨在为未来研究铺平道路，提出可能推动多模态学习系统安全协议重大进展的潜在方向。