Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing conditions. To counter these perturbations, robust multi-modal representations are highly expected, which are positioned well away from the discriminative multi-modal decision boundary. In this paper, different from conventional empirical studies, we focus on a commonly used joint multi-modal framework and theoretically discover that larger uni-modal representation margins and more reliable integration for modalities are essential components for achieving higher robustness. This discovery can further explain the limitation of multi-modal robustness and the phenomenon that multi-modal models are often vulnerable to attacks on the specific modality. Moreover, our analysis reveals how the widespread issue, that the model has different preferences for modalities, limits the multi-modal robustness by influencing the essential components and could lead to attacks on the specific modality highly effective. Inspired by our theoretical finding, we introduce a training procedure called Certifiable Robust Multi-modal Training (CRMT), which can alleviate this influence from modality preference and explicitly regulate essential components to significantly improve robustness in a certifiable manner. Our method demonstrates substantial improvements in performance and robustness compared with existing methods. Furthermore, our training procedure can be easily extended to enhance other robust training strategies, highlighting its credibility and flexibility.

Networked manufacturing platforms have been widely used for their advantages, and integration of networked manufacturing platforms can provide a large-scale distributed cooperative environment. For commercial consideration, sometimes the integration is expected to be totally decentralized. The architecture for integration of networked manufacturing platforms and the hierarchy of federations are presented. The basic states of the federations are discussed. The factory/instance pattern is used to keep the state information, which is a key element of the federation management and other functions. Both the basic factory/instance pattern and the WS-resource factory/instance pattern are proposed in detail. Finally, the implementation is illustrated with the structure of a federated node