Few-Shot Website Fingerprinting Attack with Data Augmentation

Algorithm 1

Data augmentation optimization.

	Input: A training , and validation set.
	Output: Data augmentation with optimal parameters .
	1: Setting  =  (empty set);
	2: Sequencing data augmentation operations randomly;
	3: while Enumerating augmentation operations do
	4:  Get the search space of current augmentation ;
	5:  Using TPE on to obtain the optimal parameter , with the model trained by and ;
	6:
	7: end while
	8: return