mlsanityData to 7 Oct 2026

Deep Neural Rejection against Adversarial Examples

arXiv 1910.00470 ↗First posted 1 Oct 2019cs.CV cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at test time. In this work, we propose a deep neural rejection mechanism to detect adversarial examples, based on the idea of rejecting samples that exhibit anomalous feature representations at different network layers. With respect to competing approaches, our method does not require generating adversarial examples at training time, and it is less computationally demanding. To properly evaluate our method, we define an adaptive white-box attack that is aware of the defense mechanism and aims to bypass it. Under this worst-case setting, we empirically show that our approach outperforms previously-proposed methods that detect adversarial examples by only analyzing the feature representation provided by the output network layer.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 3; 2024: 8; 2025: 6; 2026: 1.

31 papers.

Sort:

By area:

  1. 2021Machine Learning with a Reject Option: A surveycited by 107
  2. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  3. 2021Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examplescited by 23
  4. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  5. 2021Feature Importance Guided Attack: A Model Agnostic Adversarial Attackcited by 10
  6. 2021Increasing the Confidence of Deep Neural Networks by Coverage Analysiscited by 9
  7. 2021Revisiting Model's Uncertainty and Confidences for Adversarial Example Detectioncited by 9
  8. 2024Countermeasures Against Adversarial Examples in Radio Signal Classificationcited by 5
  9. 2025Don't Lag, RAG: Training-Free Adversarial Detection Using RAGcited by 5
  10. 2023Unsupervised Adversarial Detection without Extra Model: Training Loss Should Changecited by 4
  11. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3
  12. 2022Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examplescited by 3
19 more
  1. 2022MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectorscited by 2
  2. 2023Hardening RGB-D Object Recognition Systems against Adversarial Patch Attackscited by 2
  3. 2024PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysiscited by 2
  4. 2024ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformercited by 2
  5. 2024Robust image classification with multi-modal large language modelscited by 2
  6. 2022White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defensecited by 1
  7. 2024MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deceptioncited by 1
  8. 20242DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signaturescited by 1
  9. 2025Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networkscited by 1
  10. 2022Hindi/Bengali Sentiment Analysis Using Transfer Learning and Joint Dual Input Learning with Self Attentioncited by 0
  11. 2022Adversarial Patterns: Building Robust Android Malware Classifierscited by 0
  12. 2023Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejectioncited by 0
  13. 2024Manipulating hidden-Markov-model inferences by corrupting batch datacited by 0
  14. 2024A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Modelscited by 0
  15. 2025What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shiftcited by 0
  16. 2025A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classificationcited by 0
  17. 2025Sequence-Preserving Dual-FoV Defense for Traffic Sign and Light Recognition in Autonomous Vehiclescited by 0
  18. 2025Deep learning models are vulnerable, but adversarial examples are even more vulnerablecited by 0
  19. 2026GeoDetect: Geometric Adversarial Detection for VLPscited by 0