RobustBenchHAR is a pytorch framework to boost and evaluate the adversarial transferability for Human skeletal behavior recognition. Official code for the paper:
ICLR2025 TASAR: Transfer-based Attack on Skeletal Action Recognition
Key Features of RobustBenchHAR:
- A benchmark for evaluating existing transfer-based attacks in human Activity Recognition (HAR): RobustBenchHAR ensembles existing transfer-based attacks including several types and fairly evaluates various transfer-based attacks under the same setting.
- Evaluate the robustness of various models and datasets: RobustBenchHAR provides a plug-and-play interface to verify the robustness of models on different data sets.
- A summary of transfer-based attacks and defenses: RobustBenchHAR reviews numerous transfer-based attacks and adversarial defenses, making it easy to get the whole picture of transfer-based attacks for practitioners.
The complete code will be available soon.