mlsanityData to 14 Oct 2026

Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs

arXiv 2303.13211 ↗First posted 23 Mar 2023cs.CR cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. Building on these findings, we propose FREAK, a frequency-based poisoned sample detection algorithm that is simple yet effective. Our experimental results demonstrate the efficacy of FREAK not only against frequency backdoor attacks but also against some spatial attacks. Our work is just the first step in leveraging these insights. We believe that our analysis and proposed defense mechanism will provide a foundation for future research and development of backdoor defenses.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

34 of 59 references.

References · 34

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  4. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  5. 2018Spectral Signatures in Backdoor Attackscited by 484
  6. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 459
  7. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  8. 2020Backdoor Learning: A Surveycited by 426
  9. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  10. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 353
  11. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  12. 2019Label-Consistent Backdoor Attackscited by 296
22 more
  1. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  2. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 242
  3. 2019Generalized Sliced Wasserstein Distancescited by 208
  4. 2020Blind Backdoors in Deep Learning Modelscited by 182
  5. 2018Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentationcited by 180
  6. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  7. 2017Neural Trojanscited by 153
  8. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 134
  9. 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 130
  10. 2019Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detectioncited by 124
  11. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 122
  12. 2019Defending Neural Backdoors via Generative Distribution Modelingcited by 84
  13. 2020Rethinking the Trigger of Backdoor Attackcited by 77
  14. 2021FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysiscited by 61
  15. 2021Poison Ink: Robust and Invisible Backdoor Attackcited by 50
  16. 2021Topological Detection of Trojaned Neural Networkscited by 34
  17. 2021De-Pois: An Attack-Agnostic Defense against Data Poisoning Attackscited by 33
  18. 2020Defending against Backdoor Attack on Deep Neural Networkscited by 22
  19. 2021Backdoor Attack through Frequency Domaincited by 18
  20. 2021TOP: Backdoor Detection in Neural Networks via Transferability of Perturbationcited by 13
  21. 2021Check Your Other Door! Creating Backdoor Attacks in the Frequency Domaincited by 9
  22. 2023Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognitioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 2.

8 papers.

  1. 2024BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learningcited by 19
  2. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  3. 2025Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusioncited by 3
  4. 2026Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networkscited by 1
  5. 2024BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learningcited by 0
  6. 2025NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learningcited by 0
  7. 2025ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architecturescited by 0
  8. 2026Checkerboard: Closed-Form and Data-Independent Trigger Design for Clean-Label Backdoor Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
  2. 2023Towards Invisible Backdoor Attacks in the Frequency Domain against Deep Neural Networks ↗
  3. 2023UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks
  4. 2024Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
  5. 2023Stealthy Low-frequency Backdoor Attack against Deep Neural Networks
  6. 2023Mitigating Backdoors within Deep Neural Networks in Data-limited Configuration
  7. 2023Defending Against Backdoor Attacks by Layer-wise Feature Analysis
  8. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection