mlsanityData to 14 Oct 2026

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

arXiv 2404.12120 ↗First posted 18 Apr 2024cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack is one where the attacker is aware of the defenses and adapts their strategy accordingly. Our proposed method leverages adversarial training to reinforce the ability to detect attacks, without compromising clean accuracy. During the training phase, we integrate into the dataset adversarial examples, which were optimized to fool both the classifier and the adversarial detector, enabling the adversarial detector to learn and adapt to potential attack scenarios. Experimental evaluations on the CIFAR-10 and SVHN datasets demonstrate that our proposed algorithm significantly improves a detector's ability to accurately identify adaptive adversarial attacks -- without sacrificing clean accuracy.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 37 of its 54 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

37 of 54 references.

References · 37

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  8. 2016Adversarial Machine Learning at Scalecited by 936
  9. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  10. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  12. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
25 more
  1. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  2. 2017On Detecting Adversarial Perturbationscited by 232
  3. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
  4. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  5. 2023Open Sesame! Universal Black Box Jailbreaking of Large Language Modelscited by 134
  6. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  7. 2020SoK: Certified Robustness for Deep Neural Networkscited by 105
  8. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  9. 2023Content-based Unrestricted Adversarial Attackcited by 73
  10. 2017Adversarial and Clean Data Are Not Twinscited by 52
  11. 2019Deep Learning in Asset Pricingcited by 41
  12. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  13. 2022Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Priorcited by 38
  14. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 35
  15. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  16. 2019DLA: Dense-Layer-Analysis for Adversarial Example Detectioncited by 20
  17. 2020GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examplescited by 18
  18. 2023I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Modelscited by 17
  19. 2022Detecting Adversarial Perturbations in Multi-Task Perceptioncited by 15
  20. 2022Foiling Explanations in Deep Neural Networkscited by 14
  21. 2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 11
  22. 2022An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networkscited by 11
  23. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
  24. 2023New Adversarial Image Detection Based on Sentiment Analysiscited by 6
  25. 2022Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspectivecited by 11
  2. 2025Don't Lag, RAG: Training-Free Adversarial Detection Using RAGcited by 5
  3. 2025Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attackcited by 4
  4. 2025Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networkscited by 2