AdvAndMal: Adversarial Training for Android Malware Detection and Family Classification

Abstract

In recent years, Android malware has continued to evolve against detection technologies, becoming more concealed and harmful, making it difficult for existing models to resist adversarial sample attacks. At the current stage, the detection result is no longer the only criterion for evaluating the pros and cons of the model with its algorithms, it is also vital to take the model’s defensive ability against adversarial samples into consideration. In this study, we propose a general framework named AdvAndMal, which consists of a two-layer network for adversarial training to generate adversarial samples and improve the effectiveness of the classifiers in Android malware detection and family classification. The adversarial sample generation layer is composed of a conditional generative adversarial network called pix2pix, which can generate malware variants to extend the classifiers’ training set, and the malware classification layer is trained by RGB image visualized from the sequence of system calls. To evaluate the adversarial training effect of the framework, we propose the robustness coefficient, a symmetric interval i = [−1, 1], and conduct controlled experiments on the dataset to measure the robustness of the overall framework for the adversarial training. Experimental results on 12 families with the largest number of samples in the Drebin dataset show that the accuracy of the overall framework is increased from 0.976 to 0.989, and its robustness coefficient is increased from 0.857 to 0.917, which proves the effectiveness of the adversarial training method.

Visualising Static Features and Classifying Android Malware Using a Convolutional Neural Network Approach

“…Wang et al obtained the API call sequences in the smali file using the Apktool [55] tool [56]. Each *.smali file contained ".class", ".super", ".implements", and ".invoke" related identifiers and object class, super class, interface, and API calls [56]. In this way, all internal function elements of the applications were obtained [56].…”

“…Each *.smali file contained ".class", ".super", ".implements", and ".invoke" related identifiers and object class, super class, interface, and API calls [56]. In this way, all internal function elements of the applications were obtained [56]. A feature database for the system APIs was created and used as a basis for the next feature sequence analysis and visualisation, which contains a total of 50,998 methods in 5858 Android API classes from level 1 to 30, with a fixed colour value setting for each system method [56].…”

“…A feature database for the system APIs was created and used as a basis for the next feature sequence analysis and visualisation, which contains a total of 50,998 methods in 5858 Android API classes from level 1 to 30, with a fixed colour value setting for each system method [56]. The Depthfirst search algorithm was used to generate a system-level API call sequence for all internal function call methods in the application one by one [56]. Their system obtained an accuracy of 98.9% and a robustness coefficient of 91.7% with the CNN and CGAN algorithms [56].…”

IoT-Based Android Malware Detection Using Graph Neural Network With Adversarial Defense

“…The work uses sequences of permissions, actions, and APIs of the Android application as a feature vector to train the GAN. Imagebased classification and GAN-based attack are proposed in [30] where system calls of API are used as features to generate RGB images and uses pix2pix adversarial network to generate adversarial examples. Opcode-based image and a GAN is used to generate adversarial example in [31].…”

Do You Think You Can Hold Me? The Real Challenge of Problem-Space Evasion Attacks

“…Recent works[9,31,[73][74][75] used a similar approach, choosing the Drebin dataset as their source for malicious APKs and Androzoo as their source of benign apps.…”