arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.05355cs.CYcs.AI
收藏

安全多模态学习系统综述

A Survey on Safe Multi-Modal Learning System

University of Southern California(南加州大学);Rensselaer Polytechnic Institute(伦斯勒理工学院);University of Illinois Chicago(芝加哥大学伊利诺伊分校)

Tianyi Zhao, Liangliang Zhang, Yao Ma, Lu Cheng

AI总结:

本文提出首个多模态学习系统安全分类体系,围绕鲁棒性、对齐、监控和可控性四支柱,综述现有方法并指出未来研究方向。

摘要:

在人工智能快速发展的背景下,多模态学习系统(MMLS)因其处理和整合来自不同模态输入信息的能力而受到广泛关注。它们在医疗保健等关键领域的应用日益广泛,使得安全保障成为一项关键关切。然而,缺乏对其安全性的系统性研究是该领域进展的重大障碍。为弥补这一空白,我们提出了首个系统性地分类和评估MMLS安全性的分类体系。该分类体系围绕确保MMLS安全至关重要的四个基本支柱构建:鲁棒性、对齐、监控和可控性。利用这一分类体系,我们回顾了现有方法、基准和当前研究状态,同时指出了主要局限性和知识空白。最后,我们讨论了MMLS安全中的独特挑战。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MMLS安全协议取得重大进展的潜在方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑