Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features

Abstract

Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success in solving them. Despite their success, little is known about their robustness to adversarial attacks. In this paper, we propose a novel adversarial framework referred to as Time-Series Attacks via STATistical Features (TSA-STAT)}. To address the unique challenges of time-series domain, TSA-STAT employs constraints on statistical features of the time-series data to construct adversarial examples. Optimized polynomial transformations are used to create attacks that are more effective (in terms of successfully fooling DNNs) than those based on additive perturbations. We also provide certified bounds on the norm of the statistical features for constructing adversarial examples. Our experiments on diverse real-world benchmark datasets show the effectiveness of TSA-STAT in fooling DNNs for time-series domain and in improving their robustness. The source code of TSA-STAT algorithms is available at https://github.com/tahabelkhouja/Time-Series-Attacks-via-STATistical-Features

arXiv commentPublished at Journal of Artificial Intelligence Research

References in corpus (19)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Ensemble Adversarial Training: Attacks and Defenses
• Synthesizing Robust Adversarial Examples
• Certified Defenses against Adversarial Examples
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Highly comparative feature-based time-series classification
• Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
• Spatially Transformed Adversarial Examples
• Distributed and parallel time series feature extraction for industrial big data applications
• Certified Adversarial Robustness with Additive Noise
• Towards Crafting Text Adversarial Samples
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• TSViz: Demystification of Deep Learning Models for Time-Series Analysis
• Functional Adversarial Attacks
• Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
• Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
• RayS: A Ray Searching Method for Hard-label Adversarial Attack
• A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
• Improved Adversarial Training via Learned Optimizer

Cited by in corpus (3)

• Dynamic Time Warping based Adversarial Framework for Time-Series Domain
• Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
• Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble