As machine-learning (ML) based systems for malware detection become more prevalent, it becomes necessary to quantify the benefits compared to the more traditional anti-virus (AV) systems widely used today. It is not practical to build an agreed upon test set to benchmark malware detection systems on pure classification performance. Instead we tackle the problem by creating a new testing methodology, where we evaluate the change in performance on a set of known benign & malicious files as adversarial modifications are performed. The change in performance combined with the evasion techniques then quantifies a system's robustness against that approach. Through these experiments we are able to show in a quantifiable way how purely ML based systems can be more robust than AV products at detecting malware that attempts evasion through modification, but may be slower to adapt in the face of significantly novel attacks.
The short note presents an image classification dataset consisting of 10 executable code varieties and approximately 50,000 virus examples. The malicious classes include 9 families of computer viruses and one benign set. The image formatting for the first 1024 bytes of the Portable Executable (PE) mirrors the familiar MNIST handwriting dataset, such that most of the previously explored algorithmic methods can transfer with minor modifications. The designation of 9 virus families for malware derives from unsupervised learning of class labels; we discover the families with KMeans clustering that…
Behavioral malware detection aims to improve on the performance of static signature-based techniques used by anti-virus systems, which are less effective against modern polymorphic and metamorphic malware. Behavioral malware classification aims to go beyond the detection of malware by also identifying a malware's family according to a naming scheme such as the ones used by anti-virus vendors. Behavioral malware classification techniques use run-time features, such as file system or network activities, to capture the behavioral characteristic of running processes. The increasing volume of malwa…
Gebze Technical University（盖布泽技术大学）；Kadir Has University（卡迪尔哈斯大学）
Nowadays, malware and malware incidents are increasing daily, even with various antivirus systems and malware detection or classification methodologies. Machine learning techniques have been the main focus of the security experts to detect malware and determine their families. Many static, dynamic, and hybrid techniques have been presented for that purpose. In this study, the static analysis technique has been applied to malware samples to extract API calls, which is one of the most used features in machine/deep learning models as it represents the behavior of malware samples. Since the rapid …
MH-1M: A 1.34 Million-Sample Comprehensive Multi-Feature Android Malware Dataset for Machine Learning, Deep Learning, Large Language Models, and Threat Intelligence Research
Federal University of Amazonas（亚马逊联邦大学）；Institute of Computing（计算学院）；Federal University of Pampa（帕姆帕联邦大学）；AI Horizon Labs（AI地平线实验室）
Both malware and antivirus detection tools advance in their capabilities. Malware aim is to evade the detection while antivirus is to detect the malware. Over time, the detection techniques evolved from simple static signature matching over antiheuristic analysis to machine learning assisted algorithms. This thesis describes several layers of anti-virus evasion deployed by the malware and conducts the analysis of the evasion success rate. The scientific contribution of this research is in the following techniques the malware used -- the new algorithm for identifying the Windows operating syste…
The malware analysis and detection research community relies on the online platform VirusTotal to label Android apps based on the scan results of around 60 antiviral scanners. Unfortunately, there are no standards on how to best interpret the scan results acquired from VirusTotal, which leads to the utilization of different threshold-based labeling strategies (e.g., if ten or more scanners deem an app malicious, it is considered malicious). While some of the utilized thresholds may be able to accurately approximate the ground truths of apps, the fact that VirusTotal changes the set and version…
In training their newly-developed malware detection methods, researchers rely on threshold-based labeling strategies that interpret the scan reports provided by online platforms, such as VirusTotal. The dynamicity of this platform renders those labeling strategies unsustainable over prolonged periods, which leads to inaccurate labels. Using inaccurately labeled apps to train and evaluate malware detection methods significantly undermines the reliability of their results, leading to either dismissing otherwise promising detection approaches or adopting intrinsically inadequate ones. The infeasi…
Although anti-virus software has significantly evolved over the last decade, classic signature matching based on byte patterns is still a prevalent concept for identifying security threats. Anti-virus signatures are a simple and fast detection mechanism that can complement more sophisticated analysis strategies. However, if signatures are not designed with care, they can turn from a defensive mechanism into an instrument of attack. In this paper, we present a novel method for automatically deriving signatures from anti-virus software and demonstrate how the extracted signatures can be used to …
Sardar Patel Institute of Technology（萨达尔·帕特尔技术学院）；University of Mumbai（孟买大学）
Malicious software is abundant in a world of innumerable computer users, who are constantly faced with these threats from various sources like the internet, local networks and portable drives. Malware is potentially low to high risk and can cause systems to function incorrectly, steal data and even crash. Malware may be executable or system library files in the form of viruses, worms, Trojans, all aimed at breaching the security of the system and compromising user privacy. Typically, anti-virus software is based on a signature definition system which keeps updating from the internet and thus k…
Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Telefónica Digital Identity & Privacy（西班牙电信数字身份与隐私部门）
Multi-scanner Antivirus systems provide insightful information on the nature of a suspect application; however there is often a lack of consensus and consistency between different Anti-Virus engines. In this article, we analyze more than 250 thousand malware signatures generated by 61 different Anti-Virus engines after analyzing 82 thousand different Android malware applications. We identify 41 different malware classes grouped into three major categories, namely Adware, Harmful Threats and Unknown or Generic signatures. We further investigate the relationships between such 41 classes using co…
With the increase in the variety and quantity of malware, there is an urgent need to speed up the diagnosis and the analysis of malware. Extracting the malware family-related tokens from AV (Anti-Virus) labels, provided by online anti-virus engines, paves the way for pre-diagnosing the malware. Automatically extract the vital information from AV labels will greatly enhance the detection ability of security enterprises and equip the research ability of security analysts. Recent works like AVCLASS and AVCLASS2 try to extract the attributes of malware from AV labels and establish the taxonomy bas…
Malware creators have been getting their way for too long now. String-based similarity measures can leverage ground truth in a scalable way and can operate at a level of abstraction that is difficult to combat from the code level. We introduce ITect, a scalable approach to malware similarity detection based on information theory. ITect targets file entropy patterns in different ways to achieve 100% precision with 90% accuracy but it could target 100% recall instead. It outperforms VirusTotal for precision and accuracy on combined Kaggle and VirusShare malware.
During a fight between viruses and anti-viruses it is not always predictable that the anti-virus is going to win. There are many malicious viruses which target to attack and paralyze the anti-viruses. It is necessary for an anti-virus to detect and destroy the malware before its own files are detected and destroyed by the malware. The anti-virus may follow thorough testing and auditing procedures to fix all its bugs before releasing the software in the market. Besides the anti-virus may use all the obfuscation techniques like polymorphism that the viruses generally use to hide their codes. Thi…
As the anti-viruses run in a trusted kernel level any loophole in the anti-virus program can enable attackers to take full control over the computer system and steal data or do serious damages. Hence the anti-virus engines must be developed with proper security in mind. The ant-virus should be able to any type of specially created executable files, compression packages or documents that are intentionally created to exploit the anti-virus weakness. Viruses are present in almost every system even though there are anti-viruses installed. This is because every anti-virus, however good it may be, l…
As the COVID-19 pandemic emerged in early 2020, a number of malicious actors have started capitalizing the topic. Although a few media reports mentioned the existence of coronavirus-themed mobile malware, the research community lacks the understanding of the landscape of the coronavirus-themed mobile malware. In this paper, we present the first systematic study of coronavirus-themed Android malware. We first make efforts to create a daily growing COVID-19 themed mobile app dataset, which contains 4,322 COVID-19 themed apk samples (2,500 unique apps) and 611 potential malware samples (370 uniqu…
Computer malware and biological pathogens often use similar mechanisms of infections. For this reason, it has been suggested to model malware spread using epidemiological models developed to characterize the spread of biological pathogens. However, most work examining the similarities between malware and pathogens using such methods was based on theoretical analysis and simulation. Here we extend the classical Susceptible-Infected-Recovered (SIR) epidemiological model to describe two of the most common infection methods used by malware. We fit the proposed model to malware collected over a per…
Thapar Institute of Engineering and Technology（塔帕尔工程技术学院）；Savitribai Phule Pune University（萨维特里拜·普勒浦那大学）
Malware ascription is a relatively unexplored area, and it is rather difficult to attribute malware and detect authorship. In this paper, we employ various Static and Dynamic features of malicious executables to classify malware based on their family. We leverage Cuckoo Sandbox and machine learning to make progress in this research. Post analysis, classification is performed using various deep learning and machine learning algorithms. Using the features gathered from VirusTotal (static) and Cuckoo (dynamic) reports, we ran the vectorized data against Multinomial Naive Bayes, Support Vector Mac…
In evaluating detection methods, the malware research community relies on scan results obtained from online platforms such as VirusTotal. Nevertheless, given the lack of standards on how to interpret the obtained data to label apps, researchers hinge on their intuitions and adopt different labeling schemes. The dynamicity of VirusTotal's results along with adoption of different labeling schemes significantly affect the accuracies achieved by any given detection method even on the same dataset, which gives subjective views on the method's performance and hinders the comparison of different malw…
Recent advances in anti-malware technologies have steered the security industry away from maintaining vast signature databases and into newer defence technologies such as behaviour blocking, application whitelisting and others. Most would agree that the reasoning behind this is to keep up with the arms race established between malware writers and the security community almost three decades ago. Still, malware writers have not as yet created new paradigms. Indeed, malicious code development is still largely limited to code pattern changes utilizing polymorphic and metamorphic engines, as well a…
Nanjing University of Science and Technology（南京理工大学）
Malware remains a big threat to cyber security, calling for machine learning based malware detection. While promising, such detectors are known to be vulnerable to evasion attacks. Ensemble learning typically facilitates countermeasures, while attackers can leverage this technique to improve attack effectiveness as well. This motivates us to investigate which kind of robustness the ensemble defense or effectiveness the ensemble attack can achieve, particularly when they combat with each other. We thus propose a new attack approach, named mixture of attacks, by rendering attackers capable of mu…
PAD: Towards Principled Adversarial Malware Detection Against Evasion Attacks
Nanjing University of Posts and Telecommunications（南京邮电大学）；Nanjing Institute of Technology（南京工程学院）；University of Colorado Colorado Springs（科罗拉多大学斯普林斯分校）
Malware developers use combinations of techniques such as compression, encryption, and obfuscation to bypass anti-virus software. Malware with anti-analysis technologies can bypass AI-based anti-virus software and malware analysis tools. Therefore, classifying pack files is one of the big challenges. Problems arise if the malware classifiers learn packers' features, not those of malware. Training the models with unintended erroneous data turn into poisoning attacks, adversarial attacks, and evasion attacks. Therefore, researchers should consider packing to build appropriate malware classifier …
We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve the system's ability to keep pace with evolving threats. We conduct our evaluation on a sample of VirusTotal submissions spanning 2.5 years and containing 1.1 million binaries with 778GB of raw feature data. Without reviewer assistance, we achieve 72% detection at a 0.5% false positive rate, performing comparable to the best vendors on VirusTotal. Given a budg…
Comprehensive case studies on malicious code mostly focus on botnets and worms (recently revived with IoT devices), prominent pieces of malware or Advanced Persistent Threats, exploit kits, and ransomware. However, adware seldom receives such attention. Previous studies on "unwanted" Windows applications, including adware, favored breadth of analysis, uncovering ties between different actors and distribution methods. In this paper, we demonstrate the capabilities, privacy and security risks, and prevalence of a particularly successful and active adware business: Wajam, by tracking its evolutio…
Network intrusion detection systems and antivirus software are essential in detecting malicious network traffic and attacks such as denial-of-service and malwares. Each attack, worm or virus has its own distinctive signature. Signature-based intrusion detection and antivirus systems depend on pattern matching to look for possible attack signatures. Pattern matching is a very complex task, which requires a lot of time, memory and computing resources. Software-based intrusion detection is not fast enough to match high network speeds and the increasing number of attacks. In this paper, we propose…
Research shows that over the last decade, malware has been growing exponentially, causing substantial financial losses to various organizations. Different anti-malware companies have been proposing solutions to defend attacks from these malware. The velocity, volume, and the complexity of malware are posing new challenges to the anti-malware community. Current state-of-the-art research shows that recently, researchers and anti-virus organizations started applying machine learning and deep learning methods for malware analysis and detection. We have used opcode frequency as a feature vector and…
Ben-Gurion University of the Negev（本古里安大学）；Nanyang Technological University（南洋理工大学）
The performance of a machine learning-based malware classifier depends on the large and updated training set used to induce its model. In order to maintain an up-to-date training set, there is a need to continuously collect benign and malicious files from a wide range of sources, providing an exploitable target to attackers. In this study, we show how an attacker can launch a sophisticated and efficient poisoning attack targeting the dataset used to train a malware classifier. The attacker's ultimate goal is to ensure that the model induced by the poisoned dataset will be unable to detect the …
This paper describes a multi-feature dataset for training machine learning classifiers for detecting malicious Windows Portable Executable (PE) files. The dataset includes four feature sets from 18,551 binary samples belonging to five malware families including Spyware, Ransomware, Downloader, Backdoor and Generic Malware. The feature sets include the list of DLLs and their functions, values of different fields of PE Header and Sections. First, we explain the data collection and creation phase and then we explain how did we label the samples in it using VirusTotal's services. Finally, we explo…
Cybersecurity continues to be a difficult issue for society especially as the number of networked systems grows. Techniques to protect these systems range from rules-based to artificial intelligence-based intrusion detection systems and anti-virus tools. These systems rely upon the information contained in the network packets and download executables to function. Side channel information leaked from hardware has been shown to reveal secret information in systems such as encryption keys. This work demonstrates that side channel information can be used to detect malware running on a computing pl…
The topic of mobile malware detection on the Android platform has attracted significant attention over the last several years. However, while much research has been conducted toward mobile malware detection techniques, little attention has been devoted to feature selection and feature importance. That is, which app feature matters more when it comes to machine learning classification. After succinctly surveying all major, dated from 2012 to 2020, datasets used by state-of-the-art malware detection works in the literature, we analyse a critical mass of apps from the most contemporary and prevai…
The present thesis addresses the topic of denial of service capabilities detection at malware binary level, with the aim of designing a framework that integrate results from different binary analysis methods and decide on the DDoS capabilities of the analysed malware. We have implemented a process to extract meaningful data from malware samples, the extracted data was used to find characteristics and features that can lead to the detection of DDoS capabilities in binaries. Based on the discoveries, a set of rules was elaborated to detect those features in binaries. The method is tested on a da…
Carnegie Mellon University（卡内基梅隆大学）；Tel Aviv University（特拉维夫大学）；VMware；Duke University（杜克大学）；NortonLifeLock Research Group（NortonLifeLock研究组）
Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this work, we propose an attack that interweaves binary-diversification techniques and optimization frameworks to mislead such DNNs while preserving the functionality of binaries. Unlike prior attacks, ours manipulates instructions that are a functional part of the binary, which makes it particularly challenging to defend against. We evaluated our attack against thr…
Malicious email attachments are a growing delivery vector for malware. While machine learning has been successfully applied to portable executable (PE) malware detection, we ask, can we extend similar approaches to detect malware across heterogeneous file types commonly found in email attachments? In this paper, we explore the feasibility of applying machine learning as a static countermeasure to detect several types of malicious email attachments including Microsoft Office documents and Zip archives. To this end, we collected a dataset of over 5 million malicious/benign Microsoft Office docum…
In our more and more interconnected world, a specific risk is that of a cyber-epidemic (or cyber-pandemic), produced either accidentally or intentionally, where a cyber virus propagates from device to device up to undermining the global Internet system with devastating consequences in terms of economic costs and societal harms related to the shutdown of essential services. We introduce a compartmental model for studying the spreading of a malware and of the awareness of its incidence through different waves which are evolving on top of the same graph structure (the global network of connected …
Federal University of Paraná（巴拉那联邦大学）；Victoria University of Wellington（惠灵顿维多利亚大学）
Malware is a major threat to computer systems and imposes many challenges to cyber security. Targeted threats, such as ransomware, cause millions of dollars in losses every year. The constant increase of malware infections has been motivating popular antiviruses (AVs) to develop dedicated detection strategies, which include meticulously crafted machine learning (ML) pipelines. However, malware developers unceasingly change their samples' features to bypass detection. This constant evolution of malware samples causes changes to the data distribution (i.e., concept drifts) that directly affect M…
The most common malware detection approaches which are based on signature matching and are not sufficient for metamorphic malware detection, since virus kits and metamorphic engines can produce variants with no resemblance to one another. Metamorphism provides an efficient way for eluding malware detection software kits. Code obfuscation methods like dead-code insertion are also widely used in metamorphic malware. In order to address the problem of detecting mutated generations, we propose a method based on Opcode Graph Similarity (OGS). OGS tries to detect metamorphic malware using the simila…
Due to the popularity of portable document format (PDF) and increasing number of vulnerabilities in major PDF viewer applications, malware writers continue to use it to deliver malware via web downloads, email attachments and other methods in both targeted and non-targeted attacks. The topic on how to effectively block malicious PDF documents has received huge research interests in both cyber security industry and academia with no sign of slowing down. In this paper, we propose a novel approach based on a multilayer perceptron (MLP) neural network model, termed MLPdf, for the detection of PDF …
Static detection technologies based on signature-based approaches that are widely used in Android platform to detect malicious applications. It can accurately detect malware by extracting signatures from test data and then comparing the test data with the signature samples of virus and benign samples. However, this method is generally unable to detect unknown malware applications. This is because, sometimes, the machine code can be converted into assembly code, which can be easily read and understood by humans. Furthuremore, the attacker can then make sense of the assembly instructions and und…
Each day, anti-virus companies receive tens of thousands samples of potentially harmful executables. Many of the malicious samples are variations of previously encountered malware, created by their authors to evade pattern-based detection. Dealing with these large amounts of data requires robust, automatic detection approaches. This paper studies malware classification based on call graph clustering. By representing malware samples as call graphs, it is possible to abstract certain variations away, and enable the detection of structural similarities between samples. The ability to cluster simi…
By their very nature, malware samples employ a variety of techniques to conceal their malicious behavior and hide it from analysis tools. To mitigate the problem, a large number of different evasion techniques have been documented over the years, and PoC implementations have been collected in public frameworks, like the popular Al-Khaser. As malware authors tend to reuse existing approaches, it is common to observe the same evasive techniques in malware samples of different families. However, no measurement study has been conducted to date to assess the adoption and prevalence of evasion techn…
Security has become ubiquitous in every domain today as newly emerging malware pose an ever-increasing perilous threat to systems. Consequently, honeypots are fast emerging as an indispensible forensic tool for the analysis of malicious network traffic. Honeypots can be considered to be traps for hackers and intruders and are generally deployed complimentary to Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS) in a network. They help system administrators perform a rigorous analysis of external and internal attacks on their networks. They are also used by security firms …
We introduce a new malware detector - Shape-GD - that aggregates per-machine detectors into a robust global detector. Shape-GD is based on two insights: 1. Structural: actions such as visiting a website (waterhole attack) by nodes correlate well with malware spread, and create dynamic neighborhoods of nodes that were exposed to the same attack vector. However, neighborhood sizes vary unpredictably and require aggregating an unpredictable number of local detectors' outputs into a global alert. 2. Statistical: feature vectors corresponding to true and false positives of local detectors have mark…
Assemblage: Automatic Binary Dataset Construction for Machine Learning
Syracuse University（雪城大学）；Booz Allen Hamilton（博兹·艾伦·汉密尔顿公司）；University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；Laboratory for Physical Sciences（物理科学实验室）
This work focuses on a specific front of the malware detection arms-race, namely the detection of persistent, disk-resident malware. We exploit normalised compression distance (NCD), an information theoretic measure, applied directly to binaries. Given a zoo of labelled malware and benign-ware, we ask whether a suspect program is more similar to our malware or to our benign-ware. Our approach classifies malware with 97.1% accuracy and a false positive rate of 3%. We achieve our results with off-the-shelf compressors and a standard machine learning classifier and without any specialised knowled…
