mlsanityData to 14 Oct 2026

Enhancing Robustness of Machine Learning Systems via Data Transformations

arXiv 1704.02654 ↗First posted 9 Apr 2017cs.CR cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduction via Principal Component Analysis and data `anti-whitening' to enhance the resilience of machine learning, targeting both the classification and the training phase. We empirically evaluate and demonstrate the feasibility of linear transformations of data as a defense mechanism against evasion attacks using multiple real-world datasets. Our key findings are that the defense is (i) effective against the best known evasion attacks from the literature, resulting in a two-fold increase in the resources required by a white-box adversary with knowledge of the defense for a successful attack, (ii) applicable across a range of ML classifiers, including Support Vector Machines and Deep Neural Networks, and (iii) generalizable to multiple application domains, including image classification and human activity classification.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 6; 2023: 6; 2024: 12; 2025: 4.

38 papers.

Sort:

By area:

  1. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  2. 2024Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspectivecited by 28
  3. 2021"Adversarial Examples" for Proof-of-Learningcited by 20
  4. 2023False Claims against Model Ownership Resolutioncited by 17
  5. 2024Espresso: Robust Concept Filtering in Text-to-Image Modelscited by 14
  6. 2021NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Datacited by 13
  7. 2023Projected Randomized Smoothing for Certified Adversarial Robustnesscited by 11
  8. 2021Morphence: Moving Target Defense Against Adversarial Examplescited by 9
  9. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9
  10. 2022Efficient Learning of Interpretable Classification Rulescited by 5
  11. 2022AutoJoin: Efficient Adversarial Training against Gradient-Free Perturbations for Robust Maneuvering via Denoising Autoencoder and Joint Learningcited by 4
  12. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4
26 more
  1. 2024Unraveling the Key of Machine Learning-based Android Malware Detectioncited by 4
  2. 2024Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approachcited by 4
  3. 2021Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networkscited by 2
  4. 2021Sparta: Spatially Attentive and Adversarially Robust Activationcited by 2
  5. 2022Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problemcited by 2
  6. 2022Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detectioncited by 2
  7. 2023Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluationcited by 2
  8. 2024Whispers in the Machine: Confidentiality in Agentic Systemscited by 2
  9. 2021Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recovercited by 1
  10. 2021Data Synthesis for Testing Black-Box Machine Learning Modelscited by 1
  11. 2023Spatial-Frequency Discriminability for Revealing Adversarial Perturbationscited by 1
  12. 2024Robust width: A lightweight and certifiable adversarial defensecited by 1
  13. 2024MASKDROID: Robust Android Malware Detection with Masked Graph Representationscited by 1
  14. 2025Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representationcited by 1
  15. 2021DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstructioncited by 0
  16. 2021Mitigating Gradient-based Adversarial Attacks via Denoising and Compressioncited by 0
  17. 2021On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversioncited by 0
  18. 2023Survey of Trustworthy AI: A Meta Decision of AIcited by 0
  19. 2024Topological safeguard for evasion attack interpreting the neural networks' behaviorcited by 0
  20. 2024Understanding Deep Learning defenses Against Adversarial Examples Through Visualizations for Dynamic Risk Assessmentcited by 0
  21. 2024A Model for Combinatorial Dictionary Learning and Inferencecited by 0
  22. 2024LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Modelscited by 0
  23. 2024Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustnesscited by 0
  24. 2025CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detectioncited by 0
  25. 2025Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMscited by 0
  26. 2025Sparse Representations Improve Adversarial Robustness of Neural Network Classifierscited by 0