Metamorphic Malware Research Articles

Enhanced Metamorphic Techniques-A Case Study Against Havex Malware

Most of the commercial antiviruses are signature based, that is, they use existing database signature to detect the malware. Malware authors use code obfuscation techniques in their variety of malware with the aim of bypassing detection by antiviruses. Metamorphic malware change their internal structure hence evading signature based detection. For effective defense against the malware, their construction needs to be explored. This paper includes the study of different obfuscation techniques and possibilities of their extension with focus on garbage code insertion, instruction substitution and subroutine reordering. The objective is to make detection difficult by implementing subject techniques which bypass detection. Havex malware is used as a proof of concept for our antivirus evasion strategy. We have used Hidden Markov Models (HMM), which is a statistical based machine learning detection method, to test the effectiveness of our code morphing. This has shown the strength of our implemented obfuscation techniques.

Malicious Code Detection: Run Trace Output Analysis by LSTM

Malicious software threats and their detection have been gaining importance as a subdomain of information security due to the expansion of ICT applications in daily settings. A major challenge in designing and developing anti-malware systems is the coverage of the detection, particularly the development of dynamic analysis methods that can detect polymorphic and metamorphic malware efficiently. In the present study, we propose a methodological framework for detecting malicious code by analyzing run trace outputs by Long Short-Term Memory (LSTM). We developed models of run traces of malicious and benign Portable Executable (PE) files. We created our dataset from run trace outputs obtained from dynamic analysis of PE files. The obtained dataset was in the instruction format as a sequence and was called Instruction as a Sequence Model (ISM). By splitting the first dataset into basic blocks, we obtained the second one called Basic Block as a Sequence Model (BSM). The experiments showed that the ISM achieved an accuracy of 87.51% and a false positive rate of 18.34%, while BSM achieved an accuracy of 99.26% and a false positive rate of 2.62%.

Deep learning based Sequential model for malware analysis using Windows exe API Calls.

Malware development has seen diversity in terms of architecture and features. This advancement in the competencies of malware poses a severe threat and opens new research dimensions in malware detection. This study is focused on metamorphic malware, which is the most advanced member of the malware family. It is quite impossible for anti-virus applications using traditional signature-based methods to detect metamorphic malware, which makes it difficult to classify this type of malware accordingly. Recent research literature about malware detection and classification discusses this issue related to malware behavior. The main goal of this paper is to develop a classification method according to malware types by taking into consideration the behavior of malware. We started this research by developing a new dataset containing API calls made on the windows operating system, which represents the behavior of malicious software. The types of malicious malware included in the dataset are Adware, Backdoor, Downloader, Dropper, spyware, Trojan, Virus, and Worm. The classification method used in this study is LSTM (Long Short-Term Memory), which is a widely used classification method in sequential data. The results obtained by the classifier demonstrate accuracy up to 95% with 0.83 $F_1$-score, which is quite satisfactory. We also run our experiments with binary and multi-class malware datasets to show the classification performance of the LSTM model. Another significant contribution of this research paper is the development of a new dataset for Windows operating systems based on API calls. To the best of our knowledge, there is no such dataset available before our research. The availability of our dataset on GitHub facilitates the research community in the domain of malware detection to benefit and make a further contribution to this domain.

Metamorphic malware identification using engine-specific patterns based on co-opcode graphs

A metamorphic virus is a type of malware that modifies its code using a morphing engine. Morphing engines are used to generate a large number of metamorphic malware variants by performing different obfuscation techniques. Since each metamorphic malware has its own unique structure, signature based anti-virus programs are ineffective to detect these metamorphic variants. Therefore, detection of these kind of viruses becomes an increasingly important task. Recently, many researchers have focused on extracting common patterns of metamorphic variants that can be used as micro-signatures to identify the metamorphic malware executables. With the similar motivation, in this work, we propose a novel metamorphic malware identification method, named HLES-MMI (Higher-level Engine Signature based Metamorphic Malware Identification). The proposed method firstly constructs a unique graph structure, called as co-opcode graph, for each metamorphic family, then extracts engine-specific opcode patterns from the graphs. Finally, it generates higher-level signature belonging to each family by representing the extracted opcode-patterns with a binary vector. Experimental results on four datasets produced by different morphing engines demonstrate the effectiveness and efficiency of the proposed method by comparing with several existing malware identification methods.

A novel method for malware detection on ML-based visualization technique

Malware detection is one of the challenging tasks in network security. With the flourishment of network techniques and mobile devices, the threat from malwares has been of an increasing significance, such as metamorphic malwares, zero-day attack, and code obfuscation, etc. Many machine learning (ML)-based malware detection methods are proposed to address this problem. However, considering the attacks from adversarial examples (AEs) and exponential increase in the malware variant thriving nowadays, malware detection is still an active field of research. To overcome the current limitation, we proposed a novel method using data visualization and adversarial training on ML-based detectors to efficiently detect the different types of malwares and their variants. Experimental results on the MS BIG malware database and the Ember database demonstrate that the proposed method is able to prevent the zero-day attack and achieve up to 97.73% accuracy, along with 96.25% in average for all the malwares tested.

Pre-filters in-transit malware packets detection in the network

Conventional malware detection systems cannot detect most of the new malware in the network without the availability of their signatures. In order to solve this problem, this paper proposes a technique to detect both metamorphic (mutated malware) and general (non-mutated) malware in the network using a combination of known malware sub-signature and machine learning classification. This network-based malware detection is achieved through a middle path for efficient processing of non-malware packets. The proposed technique has been tested and verified using multiple data sets (metamorphic malware, non-mutated malware, and UTM real traffic), this technique can detect most of malware packets in the network-based before they reached the host better than the previous works which detect malware in host-based. Experimental results showed that the proposed technique can speed up the transmission of more than 98% normal packets without sending them to the slow path, and more than 97% of malware packets are detected and dropped in the middle path. Furthermore, more than 75% of metamorphic malware packets in the test dataset could be detected. The proposed technique is 37 times faster than existing technique.

Nonnegative matrix factorization and metamorphic malware detection

Metamorphic malware change their internal code structure by adopting code obfuscation technique while maintaining their malicious functionality during each infection. This causes change of their signature pattern across each infection and makes signature based detection particularly difficult. In this paper, through static analysis, we use similarity score from matrix factorization technique called Nonnegative Matrix Factorization for detecting challenging metamorphic malware. We apply this technique using structural compression ratio and entropy features and compare our results with previous eigenvector-based techniques. Experimental results from three malware datasets show this is a promising technique as the accuracy detection is more than 95%.

Experiments with automatic software piracy detection utilising machine-learning classifiers for micro-signatures

ABSTRACTSoftware piracy has been known as unauthorised reconstruction or illegal redistribution of a licenced software. Detecting pirated from base software is a major concern since pirated software can lead to significant financial losses as well as serious security vulnerabilities. To detect software piracy, we have recently proposed Metamorphic Analysis for Automatic Software Piracy Detection (MetaSPD) with a proof-of-concept evaluation. The core idea of MetaSPD was inspired from metamorphic malware detection due to its similarity of software piracy detection. MetaSPD works primarily based on mining the opcode graph of the base software to extract micro-signatures. Then, it leverages a classifier model to decide whether a given suspicious file is a pirated version of the base software. This paper extends our prior work in several respects. First, we present a retrospective appraisal of the main literature aiming at laying bare the status quo of software piracy detection and arguments on the current problems of the field to motivate our work. We then elaborate on MetaSPD itself and the constituent components. We provide two extensive experiments to evident the effectiveness of MetaSPD. The experiments have been carried out on two different datasets. Each dataset comprises 1300 morphed variants of the respective base software that act as pirated versions of that software. We conducted our experiments using three different classifiers. The paper is also enriched with a detailed discussion of the different properties and concerns of MetaSPD. The results corroborate that an attacker, who is using a pirated version of the given software, can hardly hide illegal usage of the software even by applying superabundant obfuscations to the code.

Improving the detection of metamorphic malware through data dependency graphs indexing

Metamorphism have been successfully used in original malicious code to the creation and proliferation of new malware instances, making them harder to detect. This work presents an approach that identifies metamorphic malware through data dependency graphs comparison. Features are extracted on data dependency graphs to build an index that is used to determine which malware family a suspicious code belongs to. Experimental results on 3045 samples of metamorphic malware showed that our proposed approach obtained accuracy rate higher than most commercial anti-malware tools.

G3MD: Mining frequent opcode sub-graphs for metamorphic malware detection of existing families

Attackers leverage various obfuscation techniques to create a metamorphic malware that can evade from detection by anti-malwares. To defeat, we propose Graph Mining for Metamorphic Malware Detection (G3MD), an intelligent system for static detection of metamorphic malwares. G3MD demonstrates one of the many aspects of what the current generation of machine-learning techniques and expert systems can do. It extends what is known about practical application of machine-learning techniques in the field of information security. It is intended to alleviate the burden of human experts and underlying costs. The novelty of G3MD is to apply graph mining on the opcode graphs of a metamorphic family of malwares to extract the frequent sub-graphs, so called micro-signatures. Based on these sub-graphs, a classifier is trained to distinguish between a benign file and a metamorphic malware. We conducted experiments on four families of metamorphic malwares common in previous studies, namely Next Generation Virus Generation Kit (NGVCK), Second Generation Virus Generator (G2), and Mass Produced Code Generation Kit (MPCGEN) viruses and Metamorphic Worm (MWOR) worms. The precision (over 99% in most cases) of metamorphic malware detection by the proposed approach corroborates its effectiveness over other existing approaches.

Music classification as a new approach for malware detection

Each year, a huge number of malicious programs are released which causes malware detection to become a critical task in computer security. Antiviruses use various methods for detecting malware, such as signature-based and heuristic-based techniques. Polymorphic and metamorphic malwares employ obfuscation techniques to bypass traditional detection methods used by antiviruses. Recently, the number of these malware has increased dramatically. Most of the previously proposed methods to detect malware are based on high-level features such as opcodes, function calls or program’s control flow graph (CFG). Due to new obfuscation techniques, extracting high-level features is tough, fallible and time-consuming; hence approaches using program’s bytes are quicker and more accurate. In this paper, a novel byte-level method for detecting malware by audio signal processing techniques is presented. In our proposed method, program’s bytes are converted to a meaningful audio signal, then Music Information Retrieval (MIR) techniques are employed to construct a machine learning music classification model from audio signals to detect new and unseen instances. Experiments evaluate the influence of different strategies converting bytes to audio signals and the effectiveness of the method.

Effective methods to detect metamorphic malware: a systematic review

The succeeding code for metamorphic malware is routinely rewritten to remain stealthy and undetected within infected environments. This characteristic is maintained by means of encryption and decryption methods, obfuscation through garbage code insertion, code transformation and registry modification which makes detection very challenging. The main objective of this study is to contribute an evidence-based narrative demonstrating the effectiveness of recent proposals. 16 primary studies were included in this analysis based on a pre-defined protocol. The majority of the reviewed detection methods used Opcode, control flow graph (CFG) and API call graph. Key challenges facing the detection of metamorphic malware include code obfuscation, lack of dynamic capabilities to analyse code and application difficulty. Methods were further analysed on the basis of their approach, limitation, empirical evidence and key parameters such as dataset, detection rate (DR) and false positive rate (FPR).

Effective methods to detect metamorphic malware: a systematic review

The succeeding code for metamorphic malware is routinely rewritten to remain stealthy and undetected within infected environments. This characteristic is maintained by means of encryption and decryption methods, obfuscation through garbage code insertion, code transformation and registry modification which makes detection very challenging. The main objective of this study is to contribute an evidence-based narrative demonstrating the effectiveness of recent proposals. 16 primary studies were included in this analysis based on a pre-defined protocol. The majority of the reviewed detection methods used Opcode, control flow graph (CFG) and API call graph. Key challenges facing the detection of metamorphic malware include code obfuscation, lack of dynamic capabilities to analyse code and application difficulty. Methods were further analysed on the basis of their approach, limitation, empirical evidence and key parameters such as dataset, detection rate (DR) and false positive rate (FPR).

An entropy-based distance measure for analyzing and detecting metamorphic malware

Metamorphic malware is a kind of malware which evades signature-based anti-viruses by changing its internal structure in each infection. This paper, firstly, introduces a new measure of distance between two computer programs called program dissimilarity measure based on entropy (PDME). Then, it suggests a measure for the degree of metamorphism, based on the suggested distance measure. The distance measure is defined based on the Entropy of the two malware programs. Moreover, the paper shows that the distance measure can be used for classifying metamorphic malware via K-Nearest Neighbors (KNN) method. The method is evaluated by four metamorphic malware families. The results demonstrate that the measure can indicate the degree of metamorphism efficiently, and the KNN classification method using PDME can classify the metamorphic malware with a high precision.

A Framework for Recognition and Confronting of Obfuscated Malwares Based on Memory Dumping and Filter Drivers

In this paper obfuscation techniques used by novel malwares presented and compared. IAT smashing, string encryption and dynamic programing are explained in static methods and hooking at user and kernel level of OS with DLL injection, modifying of SSDT and IDT table addresses, filter IRPs, and possessor emulation are techniques in dynamic methods. This paper suggest Approach for passing through malware obfuscation techniques. In order that it can analyze malware behaviors. Our methods in proposed approach are detection presence time of a malware at user and kernel level of OS, dumping of malware executable memory at correct time and precise hook installing. Main purpose of this paper is establishment of an efficient platform to analyze behavior and detect novel malwares that by use of metamorphic engine, packer and protector tools take action for obfuscation and metamorphosis of themself. At final, this paper use a dataset embeds different kind of obfuscated and metamorphic malwares in order to prove usefulness of its methods experiments. Show that proposed methods can confront most malware obfuscation techniques. It evaluated success rate to unpacking, obfuscated malwares and it shows 85% success rate to recognize kernel level malwares.

Malware Detection by Static Checking and Dynamic Analysis of Executables

The advanced malware continue to be a challenge in digital world that signature-based detection techniques fail to conquer. The malware use many anti-detection techniques to mutate. Thus no virus scanner can claim complete malware detection even for known malware. Static and dynamic analysis techniques focus upon different kinds of malware such as Evasive or Metamorphic malware. This paper proposes a comprehensive approach that combines static checking and dynamic analysis for malware detection. Static analysis is used to check the specific code characteristics. Dynamic analysis is used to analyze the runtime behavior of malware. The authors propose a framework for the automated analysis of an executable's behavior using text mining. Text mining of dynamic attributes identifies the important features for classifying the executable as benign and malware. The synergistic combination proposed in this paper allows detection of not only known variants of malware but even the obfuscated, packed and unknown malware variants and malware evasive to dynamic analysis.

SUSPEND: Determining software suspiciousness by non-stationary time series modeling of entropy signals

Commercial anti-virus software traditionally memorizes specific byte sequences (known as “signatures”) in the file contents of previously encountered malware. However, malware authors can evade signature-based detection in many ways; for instance, by using obfuscation techniques such as “packing” (encryption or compression) to hide snippets of malicious code; by writing metamorphic malware; or by tampering with existing malware. We hypothesize that certain evasion techniques can leave traces in the file’s entropy signal, revealing either similarities to known malware or the presence of tampering per se. To this end, we present SUSPEND (SUSPicious ENtropy signal Detector), an expert system which evaluates the suspiciousness of an executable file’s entropy signal in order to subserve malware classification. Whereas traditionally, entropy analysis has been used for the goal of packer detection (and therefore entropy-based features often merely comprise mean entropy or the entropy of a few file subcomponents), SUSPEND applies non-stationary time series modeling to aid in malware detection. In particular, SUSPEND (a) quantifies the “amount of structure” in the entropy signal (through detrended fluctuation analysis), (b) finds the location and size of sudden jumps in entropy (through mean change point modeling), and (c) computes the distribution of entropic variation across multiple spatial scales (through wavelet decomposition). In addition, SUSPEND (d) summarizes the entropy signal’s empirical probability distribution. Because SUSPEND’s run time can be made to scale linearly in file size, it is well-suited for large-scale malware analysis. We apply SUSPEND to a large-scale malware detection task with 500,000 heterogeneous real-world samples and over 1 million features. We find that SUSPEND boosts the predictive performance of traditional entropy analysis (as found in packer detectors) from 77.02% to 96.62%. Moreover, SUSPEND’s focus on entropy signals makes it a natural candidate for combining with other types of features; for instance, combining SUSPEND with a strings-based feature set boosts predictive accuracy from 97.18% to 98.62%. Thus, whereas traditionally, entropy analysis has focused on detecting that a file is packed, SUSPEND’s more comprehensive representation of the entropy signal helps to determine that a file is malicious. We illustrate the application of SUSPEND by studying 18 pieces of VirRansom, a family of viral ransomware which could cost millions to large organizations. SUSPEND is able to detect 100% of the studied files with over 99% confidence, whereas a more traditional strings-based model was very close to undecided and represents the entire family with a single string.

Metamorphic Malware Detection Based on Support Vector Machine Classification of Malware Sub-Signatures

Achieving accurate and efficient metamorphic malware detection remains a challenge. Metamorphic malware is able to mutate and alter its code structure in each infection, with some vital functionality and codesegment remain unchanged. We exploit these unchanged features for detecting metamorphic malware detection using Support Vector Machine(SVM) classifier. n-gram features are extracted directly from sample malware binaries to avoid disassembly, which are then masked with the extracted Snort signature n-grams. These masked features reduce considerably the number of selected n-gram features. Our method is capable to accurately detect metamorphic malware with ~99 % accuracy and low false positive rate. The proposed method is also superior than commercially available anti-viruses in detecting metamorphic malware.

Metamorphic malware detection using opcode frequency rate and decision tree

Malware is defined as any type of malicious code that is the potent to harm a computer or a network. Modern malwares are accompanied with mutation characteristics, namely polymorphism and metamorphism. They let malwares to generate enormous number of variants. Rising number of metamorphic malwares entails hardship in analyzing them for signature extraction and database updates. In spite of the broad use of signature-based methods in the security products, they are not able detect the new unseen morphs of malware, and it is stemmed from changing the structure of malware as well as the signature in each infection. In this paper, a novel method is proposed in which the proportion of opcodes is used for detecting the new morphs. Decision trees are utilized for classification and detection of malware variants based on the rate of opcode frequencies. Three metrics for evaluating the proposed method are speed, efficiency and accuracy. It was observed in the course of experiments that speed and time complexity will not be challenging factors; because of the fast nature of extracting the frequencies of opcodes from source assembly file. Empirical validation reveals that the proposed method outperforms the entire commercial antivirus programs with a high level of efficiency and accuracy.

MalwareHunt: semantics-based malware diffing speedup by normalized basic block memoization

The key challenge of software reverse engineering is that the source code of the program under investigation is typically not available. Identifying differences between two executable binaries (binary diffing) can reveal valuable information in the absence of source code, such as vulnerability patches, software plagiarism evidence, and malware variant relations. Recently, a new binary diffing method based on symbolic execution and constraint solving has been proposed to look for the code pairs with the same semantics, even though they are ostensibly different in syntactics. Such semantics-based method captures intrinsic differences/similarities of binary code, making it a compelling choice to analyze highly-obfuscated malicious programs. However, due to the nature of symbolic execution, semantics-based binary diffing suffers from significant performance slowdown, hindering it from analyzing large numbers of malware samples. In this paper, we attempt to mitigate the high overhead of semantics-based binary diffing with application to malware lineage inference. We first study the key obstacles that contribute to the performance bottleneck. Then we propose normalized basic block memoization to speed up semantics-based binary diffing. We introduce an union-find set structure that records semantically equivalent basic blocks. Managing the union-find structure during successive comparisons allows direct reuse of previously computed results. Moreover, we utilize a set of enhanced optimization methods to further cut down the invocation numbers of constraint solver. We have implemented our technique, called MalwareHunt, on top of a trace-oriented binary diffing tool and evaluated it on 15 polymorphic and metamorphic malware families. We perform intra-family comparisons for the purpose of malware lineage inference. Our experimental results show that MalwareHuntcan accelerate symbolic execution from 2.8X to 5.3X (with an average 4.1X), and reduce constraint solver invocation by a factor of 3.0X to 6.0X (with an average 4.5X).