BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
Preprint
Abstract
We introduce BackdoorMBTI, the first backdoor learning toolkit and benchmark designed for multimodal evaluation across three representative modalities from eleven commonly used datasets. BackdoorMBTI provides a systematic backdoor learning pipeline, encompassing data processing, data poisoning, backdoor training, and evaluation. The generated poison datasets and backdoor models enable detailed evaluation of backdoor defense methods. Given the diversity of modalities, BackdoorMBTI facilitates systematic evaluation across different data types. Furthermore, BackdoorMBTI offers a standardized approach to handling practical factors in backdoor learning, such as issues related to data quality and erroneous labels. We anticipate that BackdoorMBTI will expedite future research in backdoor defense methods within a multimodal context. Code is available at https://anonymous.4open.science/r/BackdoorMBTI-D6A1/README.md.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Data Poisoning and Backdoor Attacks on Audio Intelligence SystemsIEEE Communications Magazine, 2023
- An Overview of Backdoor Attacks Against Deep Neural Networks and Possible DefencesIEEE Open Journal of Signal Processing, 2022
- Backdoor Learning: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2022
- Dynamic Backdoor Attacks Against Machine Learning Models2022
- Model Agnostic Defence Against Backdoor Attacks in Machine LearningIEEE Transactions on Reliability, 2022
- Use Procedural Noise to Achieve Backdoor AttackIEEE Access, 2021
- Mitigating backdoor attacks in LSTM-based text classification systems by Backdoor Keyword IdentificationNeurocomputing, 2021
- Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger2021
- A Backdoor Attack Against LSTM-Based Text Classification SystemsIEEE Access, 2019
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012