mlsanityData to 7 Oct 2026

When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures

arXiv 1909.03418 ↗First posted 8 Sep 2019cs.LG cs.AI cs.CRcited by 40

Not on the map. Why?

Abstract (arXiv)

State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of adversarial example generation methods vs. detection and prevention methods. In this research, we present a novel detection method that uses Shapley Additive Explanations (SHAP) values computed for the internal layers of a DNN classifier to discriminate between normal and adversarial inputs. We evaluate our method by building an extensive dataset of adversarial examples over the popular CIFAR-10 and MNIST datasets, and training a neural network-based detector to distinguish between normal and adversarial inputs. We evaluate our detector against adversarial examples generated by diverse state-of-the-art attacks and demonstrate its high detection accuracy and strong generalization ability to adversarial inputs generated with different attack methods.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 10; 2023: 9; 2024: 8; 2025: 6.

40 papers.

Sort:

  1. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  2. 2022"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attackscited by 24
  3. 2023Identifying regions of importance in wall-bounded turbulence through explainable deep learningcited by 15
  4. 2022Foiling Explanations in Deep Neural Networkscited by 14
  5. 2022Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planningcited by 13
  6. 2022Generalizing Adversarial Explanations with Grad-CAMcited by 9
  7. 2022A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directionscited by 8
  8. 2022Explainable Artificial Intelligence (XAI) for Internet of Things: A Surveycited by 8
  9. 2023Impacts and Risk of Generative AI Technology on Cyber Defensecited by 8
  10. 2021Explanation-Guided Diagnosis of Machine Learning Evasion Attackscited by 6
  11. 2021A Review of Explainable Artificial Intelligence in Manufacturingcited by 5
  12. 2022Improving Interpretability via Regularization of Neural Activation Sensitivitycited by 5
28 more
  1. 2024Explainable Artificial Intelligence (XAI) for Malware Analysis: A Survey of Techniques, Applications, and Open Challengescited by 5
  2. 2022Backdooring Explainable Machine Learningcited by 4
  3. 2022Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINOcited by 4
  4. 2023Relating tSNE and UMAP to Classical Dimensionality Reductioncited by 3
  5. 2024Trustworthy Actionable Perturbationscited by 3
  6. 2023On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-boxcited by 2
  7. 2025Securing Virtual Reality Experiences: Unveiling and Tackling Cybersickness Attacks with Explainable AIcited by 2
  8. 2021STARdom: an architecture for trusted and secure human-centered manufacturing systemscited by 1
  9. 2023Detection of Adversarial Physical Attacks in Time-Series Image Datacited by 1
  10. 2023X-Detect: Explainable Adversarial Patch Detection for Object Detectors in Retailcited by 1
  11. 2024Interpreting Outliers in Time Series Data through Decoding Autoencodercited by 1
  12. 2025Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applicationscited by 1
  13. 2021Towards an Explanation Space to Align Humans and Explainable-AI Teamworkcited by 0
  14. 2021Unsupervised Detection of Adversarial Examples with Model Explanationscited by 0
  15. 2021Detecting Adversaries, yet Faltering to Noise? Leveraging Conditional Variational AutoEncoders for Adversary Detection in the Presence of Noisy Imagescited by 0
  16. 2022Btech thesis report on adversarial attack detection and purification of adverserially attacked imagescited by 0
  17. 2023A Melting Pot of Evolution and Learningcited by 0
  18. 2023XFedHunter: An Explainable Federated Learning Framework for Advanced Persistent Threat Detection in SDNcited by 0
  19. 2023What Learned Representations and Influence Functions Can Tell Us About Adversarial Examplescited by 0
  20. 2024Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoorscited by 0
  21. 2024The Anatomy of Adversarial Attacks: Concept-based XAI Dissectioncited by 0
  22. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  23. 2024Explainability of Deep Neural Networks for Brain Tumor Detectioncited by 0
  24. 2024Attention Masks Help Adversarial Attacks to Bypass Safety Detectorscited by 0
  25. 2025Enhancing Adversarial Example Detection Through Model Explanationcited by 0
  26. 2025Domain-Adversarial Neural Network and Explainable AI for Reducing Tissue-of-Origin Signal in Pan-cancer Mortality Classificationcited by 0
  27. 2025Enhancing Adversarial Robustness of IoT Intrusion Detection via SHAP-Based Attribution Fingerprintingcited by 0
  28. 2025Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigationcited by 0