The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models

3 August 2021

Papers citing "The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models"

9 / 9 papers shown

Title
NaviDet: Efficient Input-level Backdoor Detection on Text-to-Image Synthesis via Neuron Activation Variation Shengfang Zhai Jiajun Li Yue Liu Huanran Chen Zhihua Tian Wenjie Qu Qingni Shen Ruoxi Jia Yinpeng Dong Jiaheng Zhang AAML 44 0 0 09 Mar 2025
BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution Xue Yang Tao Chen Lei Guo Wenbo Jiang Ji Guo Y. Li Jiaming He 84 0 0 28 Feb 2025
Backdoor Attacks against Image-to-Image Networks Wenbo Jiang Hongwei Li Jiaming He Rui Zhang Guowen Xu Tianwei Zhang Rongxing Lu AAML 33 2 0 15 Jul 2024
Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models Changjiang Li Ren Pang Bochuan Cao Jinghui Chen Fenglong Ma Shouling Ji Ting Wang DiffM 27 3 0 14 Jun 2024
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning Shengfang Zhai Yinpeng Dong Qingni Shen Shih-Chieh Pu Yuejian Fang Hang Su 30 70 0 07 May 2023
TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets Weixin Chen D. Song Bo-wen Li DiffM 21 73 0 10 Mar 2023
How to Backdoor Diffusion Models? Sheng-Yen Chou Pin-Yu Chen Tsung-Yi Ho DiffM SILM 14 94 0 11 Dec 2022
A Style-Based Generator Architecture for Generative Adversarial Networks Tero Karras S. Laine Timo Aila 262 10,320 0 12 Dec 2018
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks E. Choi Siddharth Biswal B. Malin J. Duke Walter F. Stewart Jimeng Sun SyDa GAN 145 568 0 19 Mar 2017