SoK: Unifying Cybersecurity and Cybersafety of Multimodal Foundation Models with an Information Theory Approach

Multimodal foundation models (MFMs) represent a significant advancement in artificial intelligence, combining diverse data modalities to enhance learning and understanding across a wide range of applications. However, this integration also brings unique safety and security challenges. In this paper,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Sun, Ruoxi, Chang, Jiamin, Hammond Pearce, Xiao, Chaowei, Li, Bo, Wu, Qi, Nepal, Surya, Xue, Minhui
Format: Article
Language:English
Subjects:
Artificial intelligence
Channel capacity
Cybersecurity
Information theory
Taxonomy
Threat evaluation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multimodal foundation models (MFMs) represent a significant advancement in artificial intelligence, combining diverse data modalities to enhance learning and understanding across a wide range of applications. However, this integration also brings unique safety and security challenges. In this paper, we conceptualize cybersafety and cybersecurity in the context of multimodal learning and present a comprehensive Systematization of Knowledge (SoK) to unify these concepts in MFMs, identifying key threats to these models. We propose a taxonomy framework grounded in information theory, evaluating and categorizing threats through the concepts of channel capacity, signal, noise, and bandwidth. This approach provides a novel framework that unifies model safety and system security in MFMs, offering a more comprehensive and actionable understanding of the risks involved. We used this to explore existing defense mechanisms, and identified gaps in current research - particularly, a lack of protection for alignment between modalities and a need for more systematic defense methods. Our work contributes to a deeper understanding of the security and safety landscape in MFMs, providing researchers and practitioners with valuable insights for improving the robustness and reliability of these models.
ISSN:2331-8422