MASKDROID: Robust Android Malware Detection with Masked Graph Representations
Not on the map. Why?
Abstract (arXiv)
Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malware detection, graph representations (e.g., function call graphs) have played a pivotal role in characterizing the behaviors of Android apps. However, though achieving impressive performance in malware detection, current state-of-the-art graph-based malware detectors are vulnerable to adversarial examples. These adversarial examples are meticulously crafted by introducing specific perturbations to normal malicious inputs. To defend against adversarial attacks, existing defensive mechanisms are typically supplementary additions to detectors and exhibit significant limitations, often relying on prior knowledge of adversarial examples and failing to defend against unseen types of attacks effectively. In this paper, we propose MASKDROID, a powerful detector with a strong discriminative ability to identify malware and remarkable robustness against adversarial attacks. Specifically, we introduce a masking mechanism into the Graph Neural Network (GNN) based framework, forcing MASKDROID to recover the whole input graph using a small portion (e.g., 20%) of randomly selected nodes.This strategy enables the model to understand the malicious semantics and learn more stable representations, enhancing its robustness against adversarial attacks. While capturing stable malicious semantics in the form of dependencies inside the graph structures, we further employ a contrastive module to encourage MASKDROID to learn more compact representations for both the benign and malicious classes to boost its discriminative power in detecting malware from benign apps and adversarial examples.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 67 references that are in the map. First posted on arXiv 29 Sep 2024.
Builds on
27 of 67 references.
References · 27
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
- 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
15 more
- 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 77
- 2017Generating Adversarial Malware Examples for Black-Box Attacks Based on GANcited by 75
- 2017Enhancing Robustness of Machine Learning Systems via Data Transformationscited by 38
- 2020Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detectioncited by 33
- 2018Adversarial Deep Learning for Robust Detection of Binary Encoded Malwarecited by 32
- 2016MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Modelscited by 30
- 2020MASKER: Masked Keyword Regularization for Reliable Text Classificationcited by 25
- 2018Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detectioncited by 19
- 2021Deep Learning for Android Malware Defenses: a Systematic Literature Reviewcited by 18
- 2020Why an Android App is Classified as Malware? Towards Malware Classification Interpretationcited by 16
- 2023Black-box Adversarial Example Attack towards FCG Based Android Malware Detection under Incomplete Feature Informationcited by 13
- 2020Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detectioncited by 12
- 2023Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Settingcited by 10
- 2016Adversary Resistant Deep Neural Networks with an Application to Malware Detectioncited by 9
- 2021HomDroid: Detecting Android Covert Malware by Social-Network Homophily Analysiscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.