mlsanityData to 14 Oct 2026

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics

arXiv 1612.07767 ↗First posted 22 Dec 2016cs.CVcited by 77

Not on the map. Why?

Abstract (arXiv)

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on detecting those adversarial examples by analyzing whether they come from the same distribution as the normal examples. Instead of directly training a deep neural network to detect adversarials, a much simpler approach was proposed based on statistics on outputs from convolutional layers. A cascade classifier was designed to efficiently detect adversarials. Furthermore, trained from one particular adversarial generating mechanism, the resulting classifier can successfully detect adversarials from a completely different mechanism as well. The resulting classifier is non-subdifferentiable, hence creates a difficulty for adversaries to attack by using the gradient of the classifier. After detecting adversarial examples, we show that many of them can be recovered by simply performing a small average filter on the image. Those findings should lead to more insights about the classification mechanisms in deep convolutional neural networks.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 33; 2022: 14; 2023: 16; 2024: 7; 2025: 5; 2026: 2.

77 papers.

Sort:

By area:

  1. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  2. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  3. 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 40
  4. 2021Biometrics: Trust, but Verifycited by 39
  5. 2023DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protectioncited by 35
  6. 2021SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domaincited by 30
  7. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  8. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  9. 2022Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systemscited by 27
  10. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  11. 2022Robust Models are less Over-Confidentcited by 25
  12. 2021Adversarially Robust One-class Novelty Detectioncited by 24
38 more
  1. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  2. 2021Center Smoothing: Certified Robustness for Networks with Structured Outputscited by 18
  3. 2021Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devicescited by 18
  4. 2025AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defensescited by 15
  5. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  6. 2024PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questionscited by 14
  7. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  8. 2021Detecting AutoAttack Perturbations in the Frequency Domaincited by 10
  9. 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
  10. 2022Residue-Based Natural Language Adversarial Attack Detectioncited by 8
  11. 2021We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signaturecited by 6
  12. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  13. 2022Towards Adversarial Purification using Denoising AutoEncoderscited by 6
  14. 2022Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweightingcited by 6
  15. 2023Risk-optimized Outlier Removal for Robust 3D Point Cloud Classificationcited by 6
  16. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  17. 2021Forensicability of Deep Neural Network Inference Pipelinescited by 5
  18. 2024Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Trainingcited by 5
  19. 2022Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundariescited by 4
  20. 2023Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detectioncited by 4
  21. 2021ExAD: An Ensemble Approach for Explanation-based Adversarial Detectioncited by 3
  22. 2021Anomaly Detection of Adversarial Examples using Class-conditional Generative Adversarial Networkscited by 3
  23. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  24. 2021TREATED:Towards Universal Defense against Textual Adversarial Attackscited by 3
  25. 2022A Simple Approach to Adversarial Robustness in Few-shot Image Classificationcited by 3
  26. 2023SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformerscited by 3
  27. 2023Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutationscited by 3
  28. 2023Adversarial Medical Image with Hierarchical Feature Hidingcited by 3
  29. 2024A Multi-task Adversarial Attack Against Face Authenticationcited by 3
  30. 2021Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networkscited by 2
  31. 2021Error Diffusion Halftoning Against Adversarial Examplescited by 2
  32. 2022On Trace of PGD-Like Adversarial Attackscited by 2
  33. 2022Detecting Adversarial Examples in Batches -- a geometrical approachcited by 2
  34. 2022MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectorscited by 2
  35. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examplescited by 2
  36. 2025Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networkscited by 2
  37. 2021Medical Aegis: Robust adversarial protectors for medical imagescited by 1
  38. 2022Attack-Agnostic Adversarial Detectioncited by 1

50 most cited of 77 All 77 (JSON)