DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models

18 December 2023

Papers citing "DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models"

5 / 5 papers shown

Title
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning Abha Jha Ashwath Vaithinathan Aravindan Matthew Salaway Atharva Sandeep Bhide Duygu Nur Yaldiz AAML 70 0 0 21 Apr 2025
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming Y. Chen Shuo Shao Enhao Huang Yiming Li Pin-Yu Chen Zhanyue Qin Kui Ren AAML 52 3 0 22 Feb 2025
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning Baoyuan Wu Hongrui Chen Mingda Zhang Zihao Zhu Shaokui Wei Danni Yuan Mingli Zhu Ruotong Wang Li Liu Chaoxiao Shen AAML ELM 78 9 0 26 Jan 2024
Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples Wanzhu Jiang Yunfeng Diao He-Nan Wang Jianxin Sun Hao Wu Richang Hong 37 18 0 16 May 2023
DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection Yuanchun Li Jiayi Hua Haoyu Wang Chunyang Chen Yunxin Liu FedML SILM 86 75 0 18 Jan 2021