detection_pretrain.ac

class ac(args)[source]

Bases: defense

Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

basic sturcture for defense method:

  1. basic setting: args

  2. attack result(model, train data, test data)

  3. ac detection:

    1. classify data by activation results

    2. identify backdoor data according to classification results

  4. compute TPR and FPR

parser = argparse.ArgumentParser(description=sys.argv[0])
ac.add_arguments(parser)
args = parser.parse_args()
ac_method = ac(args)
if "result_file" not in args.__dict__:
args.result_file = 'defense_test_badnet'
elif args.result_file is None:
args.result_file = 'defense_test_badnet'
result = ac_method.detection(args.result_file)

Note

@article{chen2018detecting, title={Detecting backdoor attacks on deep neural networks by activation clustering}, author={Chen, Bryant and Carvalho, Wilka and Baracaldo, Nathalie and Ludwig, Heiko and Edwards, Benjamin and Lee, Taesung and Molloy, Ian and Srivastava, Biplav}, journal={arXiv preprint arXiv:1811.03728}, year={2018}}

Parameters:

args (baisc) – in the base class