Towards interpreting ML-based automated malware detection models: a survey
Not on the map. Why?
Abstract (arXiv)
Malware is being increasingly threatening and malware detectors based on traditional signature-based analysis are no longer suitable for current malware detection. Recently, the models based on machine learning (ML) are developed for predicting unknown malware variants and saving human strength. However, most of the existing ML models are black-box, which made their pre-diction results undependable, and therefore need further interpretation in order to be effectively deployed in the wild. This paper aims to examine and categorize the existing researches on ML-based malware detector interpretability. We first give a detailed comparison over the previous work on common ML model inter-pretability in groups after introducing the principles, attributes, evaluation indi-cators and taxonomy of common ML interpretability. Then we investigate the interpretation methods towards malware detection, by addressing the importance of interpreting malware detectors, challenges faced by this field, solutions for migitating these challenges, and a new taxonomy for classifying all the state-of-the-art malware detection interpretability work in recent years. The highlight of our survey is providing a new taxonomy towards malware detection interpreta-tion methods based on the common taxonomy summarized by previous re-searches in the common field. In addition, we are the first to evaluate the state-of-the-art approaches by interpretation method attributes to generate the final score so as to give insight to quantifying the interpretability. By concluding the results of the recent researches, we hope our work can provide suggestions for researchers who are interested in the interpretability on ML-based malware de-tection models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 152 references that are in the map. First posted on arXiv 15 Jan 2021.
Builds on
35 of 152 references.
References · 35
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2018Demystifying MMD GANscited by 1,268
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2016The Mythos of Model Interpretabilitycited by 716
- 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
- 2017Interpretation of Neural Networks is Fragilecited by 443
- 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
- 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 212
- 2020Generating Hierarchical Explanations on Text Classification via Feature Interaction Detectioncited by 57
23 more
- 2020Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approachcited by 37
- 2018Explainable Neural Networks based on Additive Index Modelscited by 33
- 2018Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Modelscited by 24
- 2020Interpretable Random Forests via Rule Extractioncited by 23
- 2018Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detectioncited by 21
- 2020Domain aware medical image classifier interpretation by counterfactual impact analysiscited by 17
- 2020Why an Android App is Classified as Malware? Towards Malware Classification Interpretationcited by 16
- 2017R2-D2: ColoR-inspired Convolutional NeuRal Network (CNN)-based AndroiD Malware Detectionscited by 15
- 2017Early Stage Malware Prediction Using Recurrent Neural Networkscited by 14
- 2020Adversarial TCAV -- Robust and Effective Interpretation of Intermediate Layers in Neural Networkscited by 12
- 2018Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projectionscited by 10
- 2020Adversarial Infidelity Learning for Model Interpretationcited by 9
- 2019Similarity-based Android Malware Detection Using Hamming Distance of Static Binary Featurescited by 8
- 2020MAB-Malware: A Reinforcement Learning Framework for Attacking Static Malware Classifierscited by 8
- 2018Deep Transfer Learning for Static Malware Classificationcited by 7
- 2020Prototype-based interpretation of the functionality of neurons in winner-take-all neural networkscited by 5
- 2018Explaining Black-box Android Malware Detectioncited by 4
- 2019Interpreting and Understanding Graph Convolutional Neural Network using Gradient-based Attribution Methodcited by 4
- 2019The Curious Case of Machine Learning In Malware Detectioncited by 4
- 2020Explaining the data or explaining a model? Shapley values that uncover non-linear dependenciescited by 4
- 2020Adversarial Attacks and Defenses: An Interpretation Perspectivecited by 3
- 2019DaDiDroid: An Obfuscation Resilient Tool for Detecting Android Malware via Weighted Directed Call Graph Modellingcited by 2
- 2020Interpreting Machine Learning Malware Detectors Which Leverage N-gram Analysiscited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.