An Adversarial Machine Learning Method Based on OpCode N-grams Feature in Malware Detection

Li, Xiang; Qiu, Kefan; Cheng, Qiansheng; Zhao, Gang

doi:10.1109/dsc50466.2020.00066

Cited by 18 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many service vendors limit users' queries, and attackers need to reduce the number of queries because sending a large number of queries within a short time is perceived as a scam or a threat. Lit et al proposed an adversarial machine learning model to detect malware based on opcode n-grams [25].…”

Section: Adversarial Attacks On Neural Networkmentioning

confidence: 99%

An Efficient Multi-Step Framework for Malware Packing Identification

Kim,

Moon,

Choi

2023

Preprint

View full text Add to dashboard Cite

Packing is a disruptive factor in the field of cybersecurity, as it obstructs the analysis of packed malware and prolongs the lifespan of malware samples. Malware equipped with anti-analysis technologies evades antivirus software and analysis tools. Therefore, detecting and analyzing packed malware is a technically challenging and resource-intensive task. The situation becomes even worse when malware classifiers are trained on the characteristics of packers instead of malware itself. Training models with numerous inadequate data inadvertently renders them impractical for classifying actual malware. Therefore, researchers should consider packetizing to construct practical malware classifier models. In this paper, we aim to propose an opportunity to reconcile the problem of packetizing with identifying it. We present a dataset consisting of over 200K actual malware samples. We propose a multi-step framework for classifying and identifying packed samples. The framework includes pseudo-optimal feature selection, machine learning-based classifiers, and packer identification steps. The framework preselects the top 20 important features using the CART algorithm and permutation importance in the first step. In the second step, each model trains on the preselected 20 features to classify the packed files with the highest performance. The XGBoost algorithm, trained on the features preselected by XGBoost with the permutation importance, demonstrated the best performance among all experimental scenarios, achieving an accuracy of 99.67%, an F1-Score of 99.46%, and an area under the curve of 99.98%. The proposed framework identifies the packer only for samples classified as Well-Known Packed in the third step.

show abstract

Section: Adversarial Attacks On Neural Networkmentioning

confidence: 99%

An Efficient Multi-Step Framework for Malware Packing Identification

Kim,

Moon,

Choi

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Other Miscellaneous Malware Detectors. In [77], Li et al first train ML-based malware detection models based on OpCode n-gram features, i.e., the n-gram sequence of operation codes extracted from the disassembled PE file. Then, the authors employ an interpretation model of SHAP [85] to assign each n-gram feature with an importance value and observe that the 4-gram "move + and + or + move" feature is a typical malicious feature as it almost does not appear in the benign PE samples.…”

Section: White-box Adversarial Attacks Against Pe Malware Detectionmentioning

confidence: 99%

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

Ling¹,

Wu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The malware has been being one of the most damaging threats to computers that span across multiple operating systems and various file formats. To defend against the ever-increasing and ever-evolving threats of malware, tremendous efforts have been made to propose a variety of malware detection methods that attempt to effectively and efficiently detect malware so as to mitigate possible damages as earlier as possible. Recent studies have shown that, one the one hand, existing machine learning (ML) and deep learning (DL) techniques enable the superior detection of newly emerging and previously unseen malware. However, on the other hand, ML and DL models are inherently vulnerable to adversarial attacks in the form of adversarial examples, which are maliciously generated by slightly and carefully perturbing the legitimate inputs to confuse the targeted models. Basically, adversarial attacks are initially extensively studied in the domain of computer vision like image classification, and some quickly expanded to other domains, including natural language processing, audio recognition and even malware detection which is extremely critical to computers.In this paper, we focus on malware with the file format of portable executable (PE) in the family of Windows operating systems, namely Windows PE malware, as a representative case to study the adversarial attack methods in such adversarial settings. To be specific, we start by first outlining the general learning framework of Windows PE malware detection based on ML/DL and subsequently highlighting three unique challenges of performing adversarial attacks in the context of Windows PE malware. We then conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of Windows PE malware detection. We conclude the paper by first presenting other related attacks against Windows PE malware detection beyond the adversarial attacks and then shedding light on future research directions and opportunities. In addition, a curated resource list of adversarial attacks and defenses for Windows PE malware detection is also available at https://github.com/ryderling/adversarial-attacks-and-defenses-for-windows-pe-malware-detection. CCS Concepts: • Security and privacy → Intrusion/anomaly detection and malware mitigation; • Theory of computation → Adversarial learning.

show abstract

“…SHAP (SHapley Additive exPlanations) is a unified framework for interpreting predictions which was proposed by Li et al [26]. SHAP assigns each feature an importance value for a particular prediction.…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

“…The present work is an extension of our DSC2020 submission [26]. The main addition is introducing the benign per-spective instead of only malicious perspective to achieve a bidirectional universal adversarial learning framework.…”

Section: Data Availabilitymentioning

confidence: 99%

BMOP: Bidirectional Universal Adversarial Learning for Binary OpCode Features

Li¹,

Nie²,

Zhi

et al. 2020

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

For malware detection, current state-of-the-art research concentrates on machine learning techniques. Binary n -gram OpCode features are commonly used for malicious code identification and classification with high accuracy. Binary OpCode modification is much more difficult than modification of image pixels. Traditional adversarial perturbation methods could not be applied on OpCode directly. In this paper, we propose a bidirectional universal adversarial learning method for effective binary OpCode perturbation from both benign and malicious perspectives. Benign features are those OpCodes that represent benign behaviours, while malicious features are OpCodes for malicious behaviours. From a large dataset of benign and malicious binary applications, we select the most significant benign and malicious OpCode features based on the feature SHAP value in the trained machine learning model. We implement an OpCode modification method that insert benign OpCodes into executables as garbage codes without execution and modify malicious OpCodes by equivalent replacement preserving execution semantics. The experimental results show that the benign and malicious OpCode perturbation (BMOP) method could bypass malicious code detection models based on the SVM, XGBoost, and DNN algorithms.

show abstract

An Adversarial Machine Learning Method Based on OpCode N-grams Feature in Malware Detection

Cited by 18 publications

References 14 publications

An Efficient Multi-Step Framework for Malware Packing Identification

An Efficient Multi-Step Framework for Malware Packing Identification

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

BMOP: Bidirectional Universal Adversarial Learning for Binary OpCode Features

Contact Info

Product

Resources

About