Hangzhou Hikvision Digital Technology Co., Ltd.

Contemporary Amperex Technology Limited

Haonan Yan

Wei Wang

Bin Wang

Zhihui Wang

Chao Li

Xing Wang

Kezhang Lin

Xiaohong Guan

Li Wan

Chaofeng Ban

Fangyu Huang

A systematic security protection method for a multimodal AI model is provided. The method comprises: in a security detection stage of the target multimodal AI model, according to a perceptual distance between detection data and original data determined by a trained distance-aware judgment model, obtaining detection data whose perceptual distance from the original data meets a requirement, and detecting the target multimodal AI model by using the detection data; in a case that the detection result in the detection stage is that the target multimodal AI model has a security problem, on one hand, performing security coding protection and tokenization filtering on the input of the model, on the other hand, performing multi-dimensional omnidirectional evaluation on the multimodal AI model.

Systematic security protection method for multimodal AI model, apparatus and device

Growing community of inventors

Hangzhou, China

Haonan Yan