Affiliation:
1. Department of Artificial lntelligence, School of Intormatics, Xiamen University, Xiamen 361005, China
Abstract
Deep neural networks (DNNs) are easily exposed to backdoor threats when training with poisoned training samples. Models using backdoor attack have normal performance for benign samples, and possess poor performance for poisoned samples manipulated with pre-defined trigger patterns. Currently, research on backdoor attacks focuses on image classification and object detection. In this article, we investigated backdoor attacks in facial sketch synthesis, which can be beneficial for many applications, such as animation production and assisting police in searching for suspects. Specifically, we propose a simple yet effective poison-only backdoor attack suitable for generation tasks. We demonstrate that when the backdoor is integrated into the target model via our attack, it can mislead the model to synthesize unacceptable sketches of any photos stamped with the trigger patterns. Extensive experiments are executed on the benchmark datasets. Specifically, the light strokes devised by our backdoor attack strategy can significantly decrease the perceptual quality. However, the FSIM score of light strokes is 68.21% on the CUFS dataset and the FSIM scores of pseudo-sketches generated by FCN, cGAN, and MDAL are 69.35%, 71.53%, and 72.75%, respectively. There is no big difference, which proves the effectiveness of the proposed backdoor attack method.
Funder
National Key R&D Program of China
National Science Fund for Distinguished Young Scholars
National Natural Science Foundation of China
Natural Science Foundation of Fujian Province of China
Subject
General Physics and Astronomy
Reference61 articles.
1. Face sketch synthesis from a single photo–sketch pair;Zhang;IEEE Trans. Circuits Syst. Video Technol.,2017
2. Robust face sketch style synthesis;Zhang;IEEE Trans. Image Process.,2016
3. Chang, L., Zhou, M., Han, Y., and Deng, X. (2010, January 23–26). Face sketch synthesis via sparse representation. Proceedings of the International Conference on Pattern Recognition, Istanbul, Turkey.
4. Zhang, L., Lin, L., Wu, X., Ding, S., and Zhang, L. (2015, January 13–16). End-to-end photo-sketch generation via fully convolutional representation learning. Proceedings of the International Conference Multimedia Retrieval, Melbourne, Australia.
5. A comprehensive survey to face hallucination;Wang;Int. J. Comput. Vis.,2014