mlsanityData to 13 Oct 2026

Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approaches

arXiv 2111.12631 ↗First posted 24 Nov 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

A key challenge in computer vision and deep learning is the definition of robust strategies for the detection of adversarial examples. Here, we propose the adoption of ensemble approaches to leverage the effectiveness of multiple detectors in exploiting distinct properties of the input data. To this end, the ENsemble Adversarial Detector (ENAD) framework integrates scoring functions from state-of-the-art detectors based on Mahalanobis distance, Local Intrinsic Dimensionality, and One-Class Support Vector Machines, which process the hidden features of deep neural networks. ENAD is designed to ensure high standardization and reproducibility to the computational workflow. Importantly, extensive tests on benchmark datasets, models and adversarial attacks show that ENAD outperforms all competing methods in the large majority of settings. The improvement over the state-of-the-art and the intrinsic generality of the framework, which allows one to easily extend ENAD to include any set of detectors, set the foundations for the new area of ensemble adversarial detection.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 40 of its 65 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

40 of 65 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  3. 2016Densely Connected Convolutional Networkscited by 6,707
  4. 2013Intriguing properties of neural networkscited by 5,137
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,368
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,992
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,371
  8. 2016Adversarial examples in the physical worldcited by 1,767
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,475
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,455
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,327
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,316
28 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,265
  2. 2014Striving for Simplicity: The All Convolutional Netcited by 989
  3. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 676
  4. 2020On Adaptive Attacks to Adversarial Example Defensescited by 554
  5. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 545
  6. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  7. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 467
  8. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 281
  9. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  10. 2017Detecting Adversarial Samples from Artifactscited by 244
  11. 2017On Detecting Adversarial Perturbationscited by 232
  12. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 204
  13. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  14. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  15. 2015Optimal whitening and decorrelationcited by 96
  16. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  17. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  18. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  19. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 62
  20. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  21. 2016Early Methods for Detecting Adversarial Imagescited by 36
  22. 2019Deep Neural Rejection against Adversarial Examplescited by 31
  23. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
  24. 2020A General Framework For Detecting Anomalous Inputs to DNN Classifierscited by 24
  25. 2017Robustness to Adversarial Examples through an Ensemble of Specialistscited by 21
  26. 2018Generalizable Adversarial Examples Detection Based on Bi-model Decision Mismatchcited by 7
  27. 2021Detecting OODs as datapoints with High Uncertaintycited by 7
  28. 2020Investigating the Compositional Structure Of Deep Neural Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2.

3 papers.

  1. 2025Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networkscited by 1
  2. 2022Adversarial Detection by Approximation of Ensemble Boundarycited by 0
  3. 2025FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Featurescited by 0