mlsanityData to 7 Oct 2026

Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection

arXiv 2209.02453 ↗First posted 6 Sep 2022cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are increasingly being applied in malware detection and their robustness has been widely debated. Traditionally an adversarial example generation scheme relies on either detailed model information (gradient-based methods) or lots of samples to train a surrogate model, neither of which are available in most scenarios. We propose the notion of the instance-based attack. Our scheme is interpretable and can work in a black-box environment. Given a specific binary example and a malware classifier, we use the data augmentation strategies to produce enough data from which we can train a simple interpretable model. We explain the detection model by displaying the weight of different parts of the specific binary. By analyzing the explanations, we found that the data subsections play an important role in Windows PE malware detection. We proposed a new function preserving transformation algorithm that can be applied to data subsections. By employing the binary-diversification techniques that we proposed, we eliminated the influence of the most weighted part to generate adversarial examples. Our algorithm can fool the DNNs in certain cases with a success rate of nearly 100%. Our method outperforms the state-of-the-art method . The most important aspect is that our method operates in black-box settings and the results can be validated with domain knowledge. Our analysis model can assist people in improving the robustness of malware detectors.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 57 references that are in the map. First posted on arXiv 6 Sep 2022.

Builds on

29 of 57 references.

References · 29

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  6. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  7. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  8. 2019Simple Black-box Adversarial Attackscited by 249
  9. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 164
  10. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  11. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
  12. 2017Malware Detection by Eating a Whole EXEcited by 114
17 more
  1. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 60
  2. 2018Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executablescited by 60
  3. 2020Functionality-preserving Black-box Optimization of Adversarial Windows Malwarecited by 58
  4. 2015Deep Neural Network Based Malware Detection Using Two Dimensional Binary Program Featurescited by 48
  5. 2018Microsoft Malware Classification Challengecited by 46
  6. 2018Exploring Adversarial Examples in Malware Detectioncited by 41
  7. 2019Understanding Deep Learning Techniques for Image Segmentationcited by 38
  8. 2019Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytescited by 31
  9. 2019Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binariescited by 30
  10. 2020Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detectioncited by 18
  11. 2019Activation Analysis of a Byte-Based Deep Neural Network for Malware Classificationcited by 14
  12. 2020Generating End-to-End Adversarial Examples for Malware Classifiers Using Explainabilitycited by 9
  13. 2020Explaining Deep Neural Networkscited by 9
  14. 2018Static Malware Detection & Subterfuge: Quantifying the Robustness of Machine Learning and Current Anti-Viruscited by 8
  15. 2020MAB-Malware: A Reinforcement Learning Framework for Attacking Static Malware Classifierscited by 8
  16. 2021Virus-MNIST: A Benchmark Malware Datasetcited by 5
  17. 2019Generation & Evaluation of Adversarial Examples for Malware Obfuscationcited by 1

Built on by

Not cited yet.