Robust Android Malware Detection against Adversarial Example Attacks

Li, Heng; Zhou, Shi-Yao; Yuan, Wei; Wang, Liu; Gao, Cuiying; Chen, Shuiyan

doi:10.1145/3442381.3450044

Cited by 21 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works have revealed that the CNNs could effectively find the salient statistical differences between samples in different classes [10]. Similar to the hypothesis in [14,35], we consider that malware might have special codes for attacks, and CNNs could explore the distance between malicious and benign samples. Also, several researchers point out that DSC and self-attention mechanism [52] which is widely used in natural language processing tasks have similar effects on generating final results [11,13].…”

Section: Convolution Methodsmentioning

confidence: 61%

“…Feature-based Methods. In early works, deep learning models are trained from carefully crafted malware features [7,15,16,18,26,28,34,58,63]. When checking a suspicious sample, models need to extract the specific features, process them in specific ways, and then detect malicious codes to give their results.…”

Section: Deep Malware Detectionmentioning

confidence: 99%

“…Xu et al devised a two-stage inference framework to detect Android malware on the extracted information [58]. Li et al leveraged Autoencoder (AE) to find the mutation of malicious features and got great performance [34]. Han et al extracted installation graphs from viruses and applied Graph Neural Network (GNN) to malware detection [18].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

SeqNet: An Efficient Neural Network for Automatic Malware Detection

Xu¹,

Fu²,

Bu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Malware continues to evolve rapidly, and more than 450,000 new samples are captured every day, which makes manual malware analysis impractical. However, existing deep learning detection models need manual feature engineering or require high computational overhead for long training processes, which might be laborious to select feature space and difficult to retrain for mitigating model aging. Therefore, a crucial requirement for a detector is to realize automatic and efficient detection.In this paper, we propose a lightweight malware detection model called SeqNet which could be trained at high speed with low memory required on the raw binaries. By avoiding contextual confusion and reducing semantic loss, SeqNet maintains the detection accuracy when reducing the number of parameters to only 136K. We demonstrate the effectiveness of our methods and the low training cost requirement of SeqNet in our experiments. Besides, we make our datasets and codes public to stimulate further academic research.

show abstract

Section: Convolution Methodsmentioning

confidence: 61%

Section: Deep Malware Detectionmentioning

confidence: 99%

See 1 more Smart Citation

SeqNet: An Efficient Neural Network for Automatic Malware Detection

Xu¹,

Fu²,

Bu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…According to our reviewed results, the majority of research constructs feature vectors by recording the existence of various categorical features of Android applications. Many studies create a look-up table to list all the potential features based on prior knowledge or feature selection approaches, and then build a ixed-size one-hot feature vector to represent each application [16,17,36,40,41,43,50,53,64,65,91,92,105,112,129,157,159,161,167,184,185]. For instance, Wu et al [167] identiied 158 high-risk features to construct feature vectors (including 97 API calls and 61 permissions).…”

Section: 23mentioning

confidence: 99%

Deep Learning for Android Malware Defenses: A Systematic Literature Review

Liu

Tantithamthavorn

et al. 2022

ACM Comput. Surv.

View full text Add to dashboard Cite

Malicious applications (particularly those targeting the Android platform) pose a serious threat to developers and end-users. Numerous research efforts have been devoted to developing effective approaches to defend against Android malware. However, given the explosive growth of Android malware and the continuous advancement of malicious evasion technologies like obfuscation and reflection, Android malware defense approaches based on manual rules or traditional machine learning may not be effective. In recent years, a dominant research field called deep learning (DL), which provides a powerful feature abstraction ability, has demonstrated a compelling and promising performance in a variety of areas, like natural language processing and computer vision. To this end, employing deep learning techniques to thwart Android malware attacks has recently garnered considerable research attention. Yet, no systematic literature review focusing on deep learning approaches for Android malware defenses exists. In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment. As a result, a total of 132 studies covering the period 2014-2021 were identified. Our investigation reveals that, while the majority of these sources mainly consider DL-based Android malware detection, 53 primary studies (40.1%) design defense approaches based on other scenarios. This review also discusses research trends, research focuses, challenges, and future research directions in DL-based Android malware defenses.

show abstract

“…Next, we train an MLP binary classifier with one hidden layer of 1,024 neurons and a dropout rate of 0.2. We use an MLP model because it has been successfully applied to malware classification in prior work [19,30,41,60,73].…”

Section: Experiments Setupmentioning

confidence: 99%

Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers

Yang¹,

Chen²,

Cortellazzi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet the stealthiness of such attacks is not well understood. In this paper, we investigate this phenomenon under the clean-label setting (i.e., attackers do not have complete control over the training or labeling process). Empirically, we show that existing backdoor attacks in malware classifiers are still detectable by recent defenses such as MNTD. To improve stealthiness, we propose a new attack, Jigsaw Puzzle (JP), based on the key observation that malware authors have little to no incentive to protect any other authors' malware but their own. As such, Jigsaw Puzzle learns a trigger to complement the latent patterns of the malware author's samples, and activates the backdoor only when the trigger and the latent pattern are pieced together in a sample. We further focus on realizable triggers in the problem space (e.g., software code) using bytecode gadgets broadly harvested from benign software. Our evaluation confirms that Jigsaw Puzzle is effective as a backdoor, remains stealthy against state-of-the-art defenses, and is a threat in realistic settings that depart from reasoning about feature-space only attacks. We conclude by exploring promising approaches to improve backdoor defenses.

show abstract

Robust Android Malware Detection against Adversarial Example Attacks

Cited by 21 publications

References 24 publications

SeqNet: An Efficient Neural Network for Automatic Malware Detection

SeqNet: An Efficient Neural Network for Automatic Malware Detection

Deep Learning for Android Malware Defenses: A Systematic Literature Review

Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers

Contact Info

Product

Resources

About