mlsanityData to 7 Oct 2026

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

arXiv 2207.04307 ↗First posted 9 Jul 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 33 of its 71 references that are in the map. First posted on arXiv 9 Jul 2022.

Builds on

33 of 71 references.

References · 33

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2016Adversarial examples in the physical worldcited by 1,762
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2016Universal adversarial perturbationscited by 774
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  10. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  11. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  12. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
21 more
  1. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  2. 2018Certified Defenses against Adversarial Examplescited by 305
  3. 2016Safety Verification of Deep Neural Networkscited by 262
  4. 2018Spatially Transformed Adversarial Examplescited by 195
  5. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  6. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  7. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  8. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 107
  9. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  10. 2020Deep Learning for Financial Applications : A Surveycited by 90
  11. 2019Functional Adversarial Attackscited by 82
  12. 2017Towards Crafting Text Adversarial Samplescited by 55
  13. 2019Adversarial Attacks on Deep Neural Networks for Time Series Classificationcited by 53
  14. 2019Adversarial Attacks on Time Seriescited by 40
  15. 2014Highly comparative feature-based time-series classificationcited by 39
  16. 2016Distributed and parallel time series feature extraction for industrial big data applicationscited by 29
  17. 2018A Frank-Wolfe Framework for Efficient and Effective Adversarial Attackscited by 29
  18. 2020Adversarial Examples in Deep Learning for Multivariate Time Series Regressioncited by 26
  19. 2018TSViz: Demystification of Deep Learning Models for Time-Series Analysiscited by 25
  20. 2020Improved Adversarial Training via Learned Optimizercited by 22
  21. 2017On the Limitation of Convolutional Neural Networks in Recognizing Negative Imagescited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2025Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verificationcited by 2
  2. 2025Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Modelscited by 1
  3. 2026Fortifying Time Series: DTW-Certified Robust Anomaly Detectioncited by 1
  4. 2024Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemblecited by 0
  5. 2024Certified Adversarial Robustness via Partition-based Randomized Smoothingcited by 0
  6. 2026Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attackscited by 0
  7. 2026Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignmentcited by 0