Learning transferable perturbations for image captioning

• Main Authors: WU, Hanjie, LIU, Yongtuo, CAI, Hongmin, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Adversarial example; Generative model; Image caption; Image captioning; Image features; Learn+; Learning models; Neural-networks; Robustness of neural network; State of the art; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8371; https://ink.library.smu.edu.sg/context/sis_research/article/9374/viewcontent/Learning_Transferable_Perturbations_for_Image_Captioning.pdf
• Institution: Singapore Management University

Present studies have discovered that state-of-the-art deep learning models can be attacked by small but well-designed perturbations. Existing attack algorithms for the image captioning task is time-consuming, and their generated adversarial examples cannot transfer well to other models. To generate...