mlsanityData to 7 Oct 2026

Explanation-Guided Diagnosis of Machine Learning Evasion Attacks

arXiv 2106.15820 ↗First posted 30 Jun 2021cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) models are susceptible to evasion attacks. Evasion accuracy is typically assessed using aggregate evasion rate, and it is an open question whether aggregate evasion rate enables feature-level diagnosis on the effect of adversarial perturbations on evasive predictions. In this paper, we introduce a novel framework that harnesses explainable ML methods to guide high-fidelity assessment of ML evasion attacks. Our framework enables explanation-guided correlation analysis between pre-evasion perturbations and post-evasion explanations. Towards systematic assessment of ML evasion attacks, we propose and evaluate a novel suite of model-agnostic metrics for sample-level and dataset-level correlation analysis. Using malware and image classifiers, we conduct comprehensive evaluations across diverse model architectures and complementary feature representations. Our explanation-guided correlation analysis reveals correlation gaps between adversarial samples and the corresponding perturbations performed on them. Using a case study on explanation-guided evasion, we show the broader usage of our methodology for assessing robustness of ML models.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 30 Jun 2021.

Builds on

35 of 60 references.

References · 35

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  9. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  12. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
23 more
  1. 2017Interpretation of Neural Networks is Fragilecited by 443
  2. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  3. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  4. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  5. 2016Understanding Neural Networks through Representation Erasurecited by 223
  6. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  7. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 164
  8. 2017Malware Detection by Eating a Whole EXEcited by 114
  9. 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
  10. 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 74
  11. 2018Interpretable Deep Learning under Firecited by 74
  12. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 60
  13. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 60
  14. 2017Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detectioncited by 51
  15. 2018Exploring Adversarial Examples in Malware Detectioncited by 41
  16. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
  17. 2019Evaluating Explanation Methods for Deep Learning in Securitycited by 38
  18. 2018Adversarial Deep Learning for Robust Detection of Binary Encoded Malwarecited by 32
  19. 2019Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binariescited by 30
  20. 2020Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysiscited by 20
  21. 2018Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examplescited by 19
  22. 2017Black-Box Attacks against RNN based Malware Detection Algorithmscited by 13
  23. 2020Best-Effort Adversarial Approximation of Black-Box Malware Classifierscited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 0; 2025: 2.

6 papers.

  1. 2022The Role of Machine Learning in Cybersecuritycited by 21
  2. 2021EG-Booster: Explanation-Guided Booster of ML Evasion Attackscited by 3
  3. 2022Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alikecited by 3
  4. 2023Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Surveycited by 3
  5. 2025Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devicescited by 0
  6. 2025DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysiscited by 0