BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
International Journal of Computer Vision · 2025-08 · 133 (8) · 5700-5787
DOI: 10.1007/s11263-025-02447-x ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 06.05.2025. Verfasst von Baoyuan Wu und 9 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 154 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province, National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Program.
Abstract (Originalsprache)
In recent years, backdoor learning has attracted increasing attention due to its effectiveness on investigating the adversarial vulnerability of artificial intelligence (AI) systems. Several seminal backdoor attack and defense algorithms have been developed, forming an increasingly fierce arms race. However, since backdoor learning involves various factors in different stages of an AI system (e.g., data preprocessing, model training algorithm, model activation), there have been diverse settings in existing works, causing unfair comparisons or unreliable conclusions (e.g., misleading, biased, or even false conclusions). Hence, it is urgent to build a unified and standardized benchmark of backdoor learning, such that we can track real progress and design a roadmap for the future development of this literature. To that end, we construct a comprehensive benchmark of backdoor learning, dubbed BackdoorBench. Our benchmark makes three valuable contributions to the research community. (1) We provide an integrated implementation of representative backdoor learning algorithms (currently including 20 attack algorithms and 32 defense algorithms), based on an extensible modular-based codebase. (2) We conduct comprehensive evaluations of the implemented algorithms on 4 models and 4 datasets, leading to 11,492 pairs of attack-against-defense evaluations in total. (3) Based on above evaluations, we present abundant analysis from 10 perspectives via 23 analysis tools, and reveal several inspiring insights about backdoor learning. We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning. Finally, we have created a user-friendly website at https://backdoorbench.github.io/, which collects all the important information of BackdoorBench, including the link to Codebase, Docs, Leaderboard, and Model Zoo.
Förderung
- Basic and Applied Basic Research Foundation of Guangdong Province
- National Natural Science Foundation of China
- Shenzhen Science and Technology Innovation Program
- Key R&D Projects of the Ministry of Science and Technology
Zitieren
APA
Wu, B., Chen, H., Zhang, M., Zhu, Z., Wei, S., Yuan, D., Zhu, M., Wang, R., Liu, L., & Shen, C. (2025). BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning. International Journal of Computer Vision, 133(8), 5700-5787. https://doi.org/10.1007/s11263-025-02447-x
Vancouver
Wu B, Chen H, Zhang M, Zhu Z, Wei S, Yuan D, et al. BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning. International Journal of Computer Vision. 2025;133(8):5700-5787. doi:10.1007/s11263-025-02447-x
BibTeX
@article{Wu2025,
author = {Wu, Baoyuan and Chen, Hongrui and Zhang, Mingda and Zhu, Zihao and Wei, Shaokui and Yuan, Danni and Zhu, Mingli and Wang, Ruotong and Liu, Li and Shen, Chao},
title = {BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {8},
pages = {5700--5787},
doi = {10.1007/s11263-025-02447-x}
}
EUVIMED