TY - GEN
T1 - Sequence Squeezing
T2 - 2021 International Joint Conference on Neural Networks, IJCNN 2021
AU - Rosenberg, Ishai
AU - Shabtai, Asaf
AU - Elovici, Yuval
AU - Rokach, Lior
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/18
Y1 - 2021/7/18
N2 - Adversarial examples are known to mislead deep learning models so that the models will classify them incorrectly, even in domains where such models have achieved state-of-the-art performance. Until recently, research on both adversarial attack and defense methods focused on computer vision, primarily using convolutional neural networks (CNNs). In recent years, adversarial example generation methods for recurrent neural networks (RNNs) have been published, demonstrating that RNN classifiers are also vulnerable to such attacks. In this paper, we present a novel defense method, referred to as sequence squeezing, aimed at making RNN variant (e.g., LSTM) classifiers more robust against such attacks. Our method differs from existing defense methods, which were designed only for non-sequence based models. We also implement three additional defense methods inspired by recently published CNN defense methods as baselines for our method. Using sequence squeezing, we were able to decrease the effectiveness of such adversarial attacks from 99.9% to 15%, outperforming all of the baseline defense methods.
AB - Adversarial examples are known to mislead deep learning models so that the models will classify them incorrectly, even in domains where such models have achieved state-of-the-art performance. Until recently, research on both adversarial attack and defense methods focused on computer vision, primarily using convolutional neural networks (CNNs). In recent years, adversarial example generation methods for recurrent neural networks (RNNs) have been published, demonstrating that RNN classifiers are also vulnerable to such attacks. In this paper, we present a novel defense method, referred to as sequence squeezing, aimed at making RNN variant (e.g., LSTM) classifiers more robust against such attacks. Our method differs from existing defense methods, which were designed only for non-sequence based models. We also implement three additional defense methods inspired by recently published CNN defense methods as baselines for our method. Using sequence squeezing, we were able to decrease the effectiveness of such adversarial attacks from 99.9% to 15%, outperforming all of the baseline defense methods.
UR - http://www.scopus.com/inward/record.url?scp=85116479454&partnerID=8YFLogxK
U2 - 10.1109/IJCNN52387.2021.9534432
DO - 10.1109/IJCNN52387.2021.9534432
M3 - Conference contribution
AN - SCOPUS:85116479454
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - IJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PB - Institute of Electrical and Electronics Engineers
Y2 - 18 July 2021 through 22 July 2021
ER -