mlsanityData to 14 Oct 2026

Early Methods for Detecting Adversarial Images

arXiv 1608.00530 ↗First posted 1 Aug 2016cs.LG cs.CR cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception. We deploy three methods to detect adversarial images. Adversaries trying to bypass our detectors must make the adversarial image less pathological or they will fail trying. Our best detection method reveals that adversarial images place abnormal emphasis on the lower-ranked principal components from PCA. Other detectors and a colorful saliency map are in an appendix.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 21; 2022: 9; 2023: 4; 2024: 1; 2025: 1.

36 papers.

Sort:

By area:

  1. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  2. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 48
  3. 2021Biometrics: Trust, but Verifycited by 39
  4. 2021SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domaincited by 30
  5. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  6. 2022Robust Models are less Over-Confidentcited by 25
  7. 2021Adversarially Robust One-class Novelty Detectioncited by 24
  8. 2022"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attackscited by 24
  9. 2022The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Trainingcited by 23
  10. 2021Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenescited by 12
  11. 2024textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIPcited by 11
  12. 2021SoK: Machine Learning Governancecited by 10
24 more
  1. 2021Detecting AutoAttack Perturbations in the Frequency Domaincited by 10
  2. 2021Self-Supervised Adversarial Example Detection by Disentangled Representationcited by 7
  3. 2022Towards Adversarial Purification using Denoising AutoEncoderscited by 6
  4. 2022An Adaptive Black-box Defense against Trojan Attacks (TrojDef)cited by 5
  5. 2021Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptionscited by 4
  6. 2021Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Taskscited by 4
  7. 2022Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundariescited by 4
  8. 2023Beyond Labeling Oracles: What does it mean to steal ML models?cited by 4
  9. 2021ExAD: An Ensemble Approach for Explanation-based Adversarial Detectioncited by 3
  10. 2021In-distribution adversarial attacks on object recognition models using gradient-free searchcited by 3
  11. 2021Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoisingcited by 3
  12. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3
  13. 2022Mixture GAN For Modulation Classification Resiliency Against Adversarial Attackscited by 3
  14. 2021Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistencycited by 2
  15. 2023Computational Asymmetries in Robust Classificationcited by 2
  16. 2023Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualizationcited by 2
  17. 2021Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examplescited by 0
  18. 2021Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Casescited by 0
  19. 2021Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Imagescited by 0
  20. 2021Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systemscited by 0
  21. 2022Semantic interpretation for convolutional neural networks: What makes a cat a cat?cited by 0
  22. 2022Btech thesis report on adversarial attack detection and purification of adverserially attacked imagescited by 0
  23. 2023Inference Time Evidences of Adversarial Attacks for Forensic on Transformerscited by 0
  24. 2025Sparse Representations Improve Adversarial Robustness of Neural Network Classifierscited by 0