Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning
This highlights a critical vulnerability in multimodal deep learning systems, which could impact applications relying on sensor fusion, though it is incremental as it builds on existing adversarial attack research.
The study investigated the robustness of multimodal data fusion models to adversarial attacks, finding that models like MFNet remain vulnerable even when only one sensor is attacked, indicating they do not fully utilize complementary relationships for defense.
The success of multimodal data fusion in deep learning appears to be attributed to the use of complementary in-formation between multiple input data. Compared to their predictive performance, relatively less attention has been devoted to the robustness of multimodal fusion models. In this paper, we investigated whether the current multimodal fusion model utilizes the complementary intelligence to defend against adversarial attacks. We applied gradient based white-box attacks such as FGSM and PGD on MFNet, which is a major multispectral (RGB, Thermal) fusion deep learning model for semantic segmentation. We verified that the multimodal fusion model optimized for better prediction is still vulnerable to adversarial attack, even if only one of the sensors is attacked. Thus, it is hard to say that existing multimodal data fusion models are fully utilizing complementary relationships between multiple modalities in terms of adversarial robustness. We believe that our observations open a new horizon for adversarial attack research on multimodal data fusion.