nathanReitinger/mlcb

This model is a fine-tuned version of dbernsohn/roberta-javascript on the mlcb dataset. It achieves the following results on the evaluation set:

Train Loss: 0.0463
Validation Loss: 0.0930
Train Accuracy: 0.9708
Epoch: 4

Intended uses & limitations

The model can be used to identify whether a JavaScript program is engaging in canvas fingerprinting.

Training and evaluation data

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 910, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.1291	0.1235	0.9693	0
0.0874	0.1073	0.9662	1
0.0720	0.1026	0.9677	2
0.0588	0.0950	0.9708	3
0.0463	0.0930	0.9708	4

Framework versions

Transformers 4.30.2
TensorFlow 2.11.0
Datasets 2.13.2
Tokenizers 0.13.3

Citation

@inproceedings{reitinger2021ml,
  title={ML-CB: Machine Learning Canvas Block.},
  author={Nathan Reitinger and Michelle L Mazurek},
  journal={Proc.\ PETS},
  volume={2021},
  number={3},
  pages={453--473},
  year={2021}
}

nathanReitinger
/

mlcb