Black-box Backdoor Defense via Zero-shot Image Purification
Preprint
Abstract
Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted. In this paper, we propose a novel defense framework against backdoor attacks through Zero-shot Image Purification (ZIP). Our framework can be applied to poisoned models without requiring internal information about the model or any prior knowledge of the clean/poisoned samples. Our defense framework involves two steps. First, we apply a linear transformation (e.g., blurring) on the poisoned image to destroy the backdoor pattern. Then, we use a pre-trained diffusion model to recover the missing semantic information removed by the transformation. In particular, we design a new reverse process by using the transformed image to guide the generation of high-fidelity purified images, which works in zero-shot settings. We evaluate our ZIP framework on multiple datasets with different types of attacks. Experimental results demonstrate the superiority of our ZIP framework compared to state-of-the-art backdoor defense baselines. We believe that our results will provide valuable insights for future defense methods for black-box models. Our code is available at https://github.com/sycny/ZIP.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor LearningInternational Journal of Computer Vision, 2025
- XGBD: Explanation-Guided Graph Backdoor Detection2023
- An Adaptive Black-Box Defense Against Trojan Attacks (TrojDef)IEEE Transactions on Neural Networks and Learning Systems, 2022
- Backdoor Learning: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2022
- Deep null space learning for inverse problems: convergence analysis and ratesInverse Problems, 2019
- Current trends in the development of intelligent unmanned autonomous systemsFrontiers of Information Technology & Electronic Engineering, 2017
- Predicting the Future — Big Data, Machine Learning, and Clinical MedicineNew England Journal of Medicine, 2016
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012