Adversarial Attacks on Deep Neural Networks for Time Series Classification

Abstract

Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety. With the recent success of deep neural networks in various domains such as computer vision and natural language processing, researchers started adopting these techniques for solving time series data mining problems. However, to the best of our knowledge, no previous work has considered the vulnerability of deep learning models to adversarial time series examples, which could potentially make them unreliable in situations where the decision taken by the classifier is crucial such as in medicine and security. For computer vision problems, such attacks have been shown to be very easy to perform by altering the image and adding an imperceptible amount of noise to trick the network into wrongly classifying the input image. Following this line of work, we propose to leverage existing adversarial attack mechanisms to add a special noise to the input time series in order to decrease the network's confidence when classifying instances at test time. Our results reveal that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks which can have major consequences in multiple domains such as food safety and quality assurance.

arXiv commentAccepted at IJCNN 2019

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Deep learning for time series classification: a review
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Transfer learning for time series classification
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Evaluating surgical skills from kinematic data using convolutional neural networks
• Deep Neural Network Ensembles for Time Series Classification
• Data augmentation using synthetic data for time series classification with deep residual networks

Cited by in corpus (23)

• InceptionTime: Finding AlexNet for Time Series Classification
• Deep Neural Network Ensembles for Time Series Classification
• Dynamic Time Warping based Adversarial Framework for Time-Series Domain
• Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series
• Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
• Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
• Anomalous Example Detection in Deep Learning: A Survey
• Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack
• Adversarial jamming attacks and defense strategies via adaptive deep reinforcement learning
• The Duo of Artificial Intelligence and Big Data for Industry 4.0: Review of Applications, Techniques, Challenges, and Future Research Directions
• BASAR:Black-box Attack on Skeletal Action Recognition
• RTFN: A Robust Temporal Feature Network for Time Series Classification
• Extreme-SAX: Extreme Points Based Symbolic Representation for Time Series Classification
• Developing Future Human-Centered Smart Cities: Critical Analysis of Smart City Security, Interpretability, and Ethical Challenges
• Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
• Crafting Adversarial Examples for Deep Learning Based Prognostics (Extended Version)
• Benchmarking adversarial attacks and defenses for time-series data
• Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis
• Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
• TSAX is Trending
• On Adversarial Vulnerability of PHM algorithms: An Initial Study
• ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness
• Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control