nvita
PublicThe n-Values Time Series Attack (nVITA) is a sparse indirect black-box evasion attack that aims to achieve the adversarial goal (such as enforcing a certain output of the model) on TSF models by altering n values in an input time series. This repository is based on PyTorch. It also contains the implementations of FGSM and BIM for TSF models.
adversarial-machine-learningconvolutional-neural-networksevasion-attackpytorchrecurrent-neural-networkstime-series-forecasting
Creat：2022-07-01T15:48:08
Update：2025-03-14T21:30:26
4
Stars
0
Stars Increase