Keywords: Backdoor Learning, Benchmark
Abstract: Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms race. However, we find that the evaluations of new methods are often unthorough to verify their claims and accurate performance, mainly due to the rapid development, diverse settings, and the difficulties of implementation and reproducibility. Without thorough evaluations and comparisons, it is not easy to track the current progress and design the future development roadmap of the literature. To alleviate this dilemma, we build a comprehensive benchmark of backdoor learning called BackdoorBench. It consists of an extensible modular-based codebase (currently including implementations of 8 state-of-the-art (SOTA) attacks and 9 SOTA defense algorithms) and a standardized protocol of complete backdoor learning. We also provide comprehensive evaluations of every pair of 8 attacks against 9 defenses, with 5 poisoning ratios, based on 5 models and 4 datasets, thus 8,000 pairs of evaluations in total. We present abundant analysis from different perspectives about these 8,000 evaluations, studying the effects of different factors in backdoor learning. All codes and evaluations of BackdoorBench are publicly available at https://backdoorbench.github.io.
Author Statement: Yes
TL;DR: 8 backdoor attacks; 9 backdoor defenses; 8,000 evaluations; 5 poisoning ratios; 5 models; 4 datasets; 5 analysis tools
URL: https://backdoorbench.github.io; https://github.com/SCLBD/BackdoorBench
License: The repository of BackdoorBench is licensed by The Chinese University of Hong Kong, Shenzhen and Shenzhen Research Institute of Big Data under Creative Commons Attribution-NonCommercial 4.0 International Public License (identified as CC BY-NC-4.0 in SPDX). More details of the license could be found at https://github.com/SCLBD/BackdoorBench/blob/main/LICENSE.
Supplementary Material: pdf
Contribution Process Agreement: Yes
In Person Attendance: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 6 code implementations](https://www.catalyzex.com/paper/arxiv:2206.12654/code)