Adversarial Attacks on Time Series

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-Nearest Neighbor Dynamic Time Warping (1-NN) DTW and a Fully Convolutional Network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples.

[1]  Houshang Darabi,et al.  Asymptotic Dynamic Time Warping calculation with utilizing value repetition , 2018, Knowledge and Information Systems.

[2]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[3]  Houshang Darabi,et al.  Efficient Classification of Long Time Series by 3-D Dynamic Time Warping , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Ulf Leser,et al.  Fast and Accurate Time Series Classification with WEASEL , 2017, CIKM.

[6]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[7]  Dan Boneh,et al.  Ensemble Adversarial Training: Attacks and Defenses , 2017, ICLR.

[8]  Jason Lines,et al.  Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles , 2015, IEEE Transactions on Knowledge and Data Engineering.

[9]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[10]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[11]  Shin Ishii,et al.  Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[13]  Ian S. Fischer,et al.  Adversarial Transformation Networks: Learning to Generate Adversarial Examples , 2017, ArXiv.

[14]  Rohit J. Kate.  Using dynamic time warping distances as features for improved time series classification , 2016, Data Mining and Knowledge Discovery.

[15]  Eamonn J. Keogh,et al.  Fast Shapelets: A Scalable Algorithm for Discovering Time Series Shapelets , 2013, SDM.

[16]  Dayne Freitag,et al.  A Machine Learning Architecture for Optimizing Web Search Engines , 1999 .

[17]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[18]  George Manis,et al.  Heartbeat Time Series Classification With Support Vector Machines , 2009, IEEE Transactions on Information Technology in Biomedicine.

[19]  Javier Del Ser,et al.  Adversarial Sample Crafting for Time Series Classification with Elastic Similarity Measures , 2018, IDC.

[20]  R. Venkatesh Babu,et al.  Generalizable Data-Free Objective for Crafting Universal Adversarial Perturbations , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[23]  Michael J. Pazzani,et al.  Content-Based Recommendation Systems , 2007, The Adaptive Web.

[24]  Yiran Chen,et al.  MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks , 2018, 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).

[25]  David A. Wagner,et al.  Audio Adversarial Examples: Targeted Attacks on Speech-to-Text , 2018, 2018 IEEE Security and Privacy Workshops (SPW).

[26]  Patrick Schäfer.  The BOSS is concerned with time series classification in the presence of noise , 2014, Data Mining and Knowledge Discovery.

[27]  Guang-Zhong Yang,et al.  A Deep Learning Approach to on-Node Sensor Data Analytics for Mobile or Wearable Devices , 2017, IEEE Journal of Biomedical and Health Informatics.

[28]  Houshang Darabi,et al.  Multivariate LSTM-FCNs for Time Series Classification , 2018, Neural Networks.

[29]  Chotirat Ann Ratanamahatana,et al.  A Dimensionality Reduction Technique for Time Series Classification Using Additive Representation , 2019 .

[30]  Jiashi Feng,et al.  Anticipating Where People will Look Using Adversarial Networks , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Rich Caruana,et al.  Model compression , 2006, KDD '06.

[32]  Li Wei,et al.  Fast time series classification using numerosity reduction , 2006, ICML.

[33]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[34]  Patrick D. McDaniel,et al.  Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples , 2016, ArXiv.