Malware detection using assembly and API call sequences

One of the major problems concerning information assurance is malicious code. To evade detection, malware has also been encrypted or obfuscated to produce variants that continue to plague properly defended and patched networks with zero day exploits. With malware and malware authors using obfuscation techniques to generate automated polymorphic and metamorphic versions, anti-virus software must always keep up with their samples and create a signature that can recognize the new variants. Creating a signature for each variant in a timely fashion is a problem that anti-virus companies face all the time. In this paper we present detection algorithms that can help the anti-virus community to ensure a variant of a known malware can still be detected without the need of creating a signature; a similarity analysis (based on specific quantitative measures) is performed to produce a matrix of similarity scores that can be utilized to determine the likelihood that a piece of code under inspection contains a particular malware. Two general malware detection methods presented in this paper are: Static Analyzer for Vicious Executables (SAVE) and Malware Examiner using Disassembled Code (MEDiC). MEDiC uses assembly calls for analysis and SAVE uses API calls (Static API call sequence and Static API call set) for analysis. We show where Assembly can be superior to API calls in that it allows a more detailed comparison of executables. API calls, on the other hand, can be superior to Assembly for its speed and its smaller signature. Our two proposed techniques are implemented in SAVE) and MEDiC. We present experimental results that indicate that both of our proposed techniques can provide a better detection performance against obfuscated malware. We also found a few false positives, such as those programs that use network functions (e.g. PuTTY) and encrypted programs (no API calls or assembly functions are found in the source code) when the thresholds are set 50% similarity measure. However, these false positives can be minimized, for example by changing the threshold value to 70% that determines whether a program falls in the malicious category or not.     

针对指令乱序变形技术的归一化研究

新出现的恶意代码大部分是在原有恶意代码基础上修改转换而来.许多变形恶意代码更能自动完成该过程,由于其特征码不固定,给传统的基于特征码检测手段带来了极大挑战.采用归一化方法,并结合使用传统检测技术是一种应对思路.本文针对指令乱序这种常用变形技术提出了相应的归一化方案.该方案先通过控制依赖分析将待测代码划分为若干基本控制块,然后依据数据依赖图调整各基本控制块中的指令顺序,使得不同变种经处理后趋向于一致的规范形式.该方案对指令乱序的两种实现手段,即跳转法和非跳转法,同时有效.最后通过模拟测试对该方案的有效性进行了验证.     

Behavior-based features model for malware detection

The sharing of malicious code libraries and techniques over the Internet has vastly increased the release of new malware variants in an unprecedented rate. Malware variants share similar behaviors yet they have different syntactic structure due to the incorporation of many obfuscation and code change techniques such as polymorphism and metamorphism. The different structure of malware variants poses a serious problem to signature-based detection technique, yet their similar exhibited behaviors and actions can be a remarkable feature to detect them by behavior-based techniques. Malware instances also largely depend on API calls provided by the operating system to achieve their malicious tasks. Therefore, behavior-based detection techniques that utilize API calls are promising for the detection of malware variants. In this paper, we propose a behavior-based features model that describes malicious action exhibited by malware instance. To extract the proposed model, we first perform dynamic analysis on a relatively recent malware dataset inside a controlled virtual environment and capture traces of API calls invoked by malware instances. The traces are then generalized into high-level features we refer to as actions. We assessed the viability of actions by various classification algorithms such as decision tree, random forests, and support vector machine. The experimental results demonstrate that the classifiers attain high accuracy and satisfactory results in the detection of malware variants.     

基于权限相关性的Android恶意软件检测

针对Android平台恶意软件检测需求和Android权限特征冗余的问题,提出一套从权限相关性角度快速检测恶意软件的方案。采用卡方检验计算各权限属性对于分类结果的影响大小,去除冗余权限特征,再对权限属性聚类,提取代表性权限特征,进一步减少冗余。最后利用基于不同权限特征权重的改进朴素贝叶斯算法进行软件分类。在收集的2000个软件样本上进行了实验,恶意软件漏检率为10.33%,总体预测准确率达到88.98%。实验结果表明,该方案利用少量权限特征,能够初步检测Android应用软件是否有恶意倾向,为深入判断分析提供参考依据。     

A comprehensive survey on deep learning based malware detection techniques

Recent theoretical and practical studies have revealed that malware is one of the most harmful threats to the digital world. Malware mitigation techniques have evolved over the years to ensure security. Earlier, several classical methods were used for detecting malware embedded with various features like the signature, heuristic, and others. Traditional malware detection techniques were unable to defeat new generations of malware and their sophisticated obfuscation tactics. Deep Learning is increasingly used in malware detection as DL-based systems outperform conventional malware detection approaches at finding new malware variants. Furthermore, DL-based techniques provide rapid malware prediction with excellent detection rates and analysis of different malware types. Investigating recently proposed Deep Learning-based malware detection systems and their evolution is hence of interest to this work. It offers a thorough analysis of the recently developed DL-based malware detection techniques. Furthermore, current trending malwares are studied and detection techniques of Mobile malware (both Android and iOS), Windows malware, IoT malware, Advanced Persistent Threats (APTs), and Ransomware are precisely reviewed.     

面向恶意软件检测模型的黑盒对抗攻击方法

深度学习方法已被广泛应用于恶意软件检测中并取得了较好的预测精度,但同时深度神经网络容易受到对输入数据添加细微扰动的对抗攻击,导致模型输出错误的预测结果,从而使得恶意软件检测失效。针对基于深度学习的恶意软件检测方法的安全性,提出了一种面向恶意软件检测模型的黑盒对抗攻击方法。首先在恶意软件检测模型内部结构参数完全未知的前提下,通过生成对抗网络模型来生成恶意软件样本;然后使生成的对抗样本被识别成预先设定的目标类型以实现目标攻击,从而躲避恶意软件检测;最后,在Kaggle竞赛的恶意软件数据集上展开实验,验证了所提黑盒攻击方法的有效性。进一步得到,生成的对抗样本也可对其他恶意软件检测方法攻击成功,这验证了其具有较强的攻击迁移性。     

像素归一化方法在恶意代码可视分析中的应用

恶意代码的编写者通常采用自动化的手段开发恶意代码变种,使得恶意代码的数量呈现迅猛增长的态势。由于自动化的方式会重复利用恶意代码中的核心模块,因此也为病毒研究人员辨识和区分恶意代码族提供了有利依据。借鉴灰度图的思想,利用K-Nearest Neighbor（KNN）分类算法,给出了一种新的研究恶意代码谱系分类的可视化方法。其基本思想是,通过将二进制文件转换成双色通道的位图和像素归一图,从可视化的角度标识恶意样本特性,以此实现恶意代码族的相似度比较及分类。实验结果表明采用了像素归一化的降维映射机制能显著地减小文件可视特征的呈现时间开销,且该方法以自动化操作的方式运用Jaccard距离算法进行快速相似度比较,实现了恶意代码样本的有效分类,提高了分析人员的识别效率。     

DroidChain: A novel Android malware detection method based on behavior chains

The drastic increase of Android malware has led to strong interest in automating malware analysis. In this paper, to fight against malware variants and zero-day malware, we proposed DroidChain: a method combining static analysis and a behavior chain model. We transform the malware detection problem into more accessible matrix form. Using this method, we propose four kinds of malware models, including privacy leakage, SMS financial charges, malware installation, and privilege escalation. To reduce time complexity, we propose the WxShall-extend algorithm. We had moved the prototype to GitHub and evaluate using 1260 malware samples. Experimental malware detection results demonstrate accuracy, precision, and recall of 73%–93%, 71%–99%, and 42%–92%, respectively. Calculation time accounts for 6.58% of the well-known Warshall algorithm’s expense. Results demonstrate that our method, which can detect four kinds of malware simultaneously, is better than Androguard and Kirin.     

一种基于主动学习的恶意代码检测方法

现有恶意代码的检测往往依赖于对足够数量样本的分析.然而新型恶意代码大量涌现,其出现之初,样本数量有限,现有方法无法迅速检测出新型恶意代码及其变种.本文在数据流依赖网络中分析进程访问行为异常度与相似度,引入了恶意代码检测估计风险,并提出一种通过最小化估计风险实现主动学习的恶意代码检测方法.该方法只需要很少比例的训练样本就可实现准确的恶意代码检测,较现有方法更适用于新型恶意代码检测.通过我们对真实的8,340个正常进程以及7,257个恶意代码进程的实验分析,相比于传统基于统计分类器的检测方法,本文方法明显地提升了恶意代码检测效果.即便在训练样本仅为总体样本数量1%的情况下,本文方法可以也可达到5.55%的错误率水平,比传统方法降低了36.5%.     

Architecture of a morphological malware detector

Most of malware detectors are based on syntactic signatures that identify known malicious programs. Up to now this architecture has been sufficiently efficient to overcome most of malware attacks. Nevertheless, the complexity of malicious codes still increase. As a result the time required to reverse engineer malicious programs and to forge new signatures is increasingly longer. This study proposes an efficient construction of a morphological malware detector, that is a detector which associates syntactic and semantic analysis. It aims at facilitating the task of malware analysts providing some abstraction on the signature representation which is based on control flow graphs. We build an efficient signature matching engine over tree automata techniques. Moreover we describe a generic graph rewriting engine in order to deal with classic mutations techniques. Finally, we provide a preliminary evaluation of the strategy detection carrying out experiments on a malware collection.     

Software transformations to improve malware detection

Malware is code designed for a malicious purpose, such as obtaining root privilege on a host. A malware detector identifies malware and thus prevents it from adversely affecting a host. In order to evade detection, malware writers use various obfuscation techniques to transform their malware. There is strong evidence that commercial malware detectors are susceptible to these evasion tactics. In this paper, we describe the design and implementation of a malware transformer that reverses the obfuscations performed by a malware writer. Our experimental evaluation demonstrates that this malware transformer can drastically improve the detection rates of commercial malware detectors.     

基于语义的恶意代码行为特征提取及检测方法

提出一种基于语义的恶意代码行为特征提取及检测方法,通过结合指令层的污点传播分析与行为层的语义分析,提取恶意代码的关键行为及行为间的依赖关系;然后,利用抗混淆引擎识别语义无关及语义等价行为,获取具有一定抗干扰能力的恶意代码行为特征.在此基础上,实现特征提取及检测原型系统.通过对多个恶意代码样本的分析和检测,完成了对该系统的实验验证.实验结果表明,基于上述方法提取的特征具有抗干扰能力强等特点,基于此特征的检测对恶意代码具有较好的识别能力.     

Automatic malware classification and new malware detection using machine learning

The explosive growth of malware variants poses a major threat to information security. Traditional anti-virus systems based on signatures fail to classify unknown malware into their corresponding families and to detect new kinds of malware programs. Therefore, we propose a machine learning based malware analysis system, which is composed of three modules: data processing, decision making, and new malware detection. The data processing module deals with gray-scale images, Opcode n-gram, and import functions, which are employed to extract the features of the malware. The decision-making module uses the features to classify the malware and to identify suspicious malware. Finally, the detection module uses the shared nearest neighbor (SNN) clustering algorithm to discover new malware families. Our approach is evaluated on more than 20 000 malware instances, which were collected by Kingsoft, ESET NOD32, and Anubis. The results show that our system can effectively classify the unknown malware with a best accuracy of 98.9%, and successfully detects 86.7% of the new malware.     

Using ontologies to perform threat analysis and develop defensive strategies for mobile security

Existing studies on the detection of mobile malware have focused mainly on static analyses performed to examine the code-structure signature of viruses, rather than the dynamic behavioral aspects. By contrast, the unidentified behavior of new mobile viruses using the self-modification, polymorphic, and mutation techniques for variants have largely been ignored. The problem of precision regarding malware variant detection has become one of the key concerns in mobile security. Accordingly, the present study proposed a threat risk analysis model for mobile viruses, using a heuristic approach incorporating both malware behavior analysis and code analysis to generate a virus behavior ontology associated with the Protégé platform. The proposed model can not only explicitly identify an attack profile in accordance with structural signature of mobile viruses, but also overcome the uncertainty regarding the probability of an attack being successful. This model is able to achieve this by extending frequent episode rules to investigate the attack profile of a given malware, using specific event sequences associated with the sandbox technique for mobile applications (apps) and hosts. For probabilistic analysis, defense evaluation metrics for each node were used to simulate the results of an attack. The simulations focused specifically on the attack profile of a botnet to assess the threat risk. The validity of the proposed approach was demonstrated numerically by using two malware cyber-attack examples. Overall, the results presented in this paper prove that the proposed scheme offers an effective countermeasure, evaluated using a set of security metrics, for mitigating network threats by considering the interaction between the attack profiles and defense needs.     

Fragmented malware through RFID and its defenses

Malware, in essence, is an infiltration to one’s computer system. Malware is created to wreak havoc once it gets in through weakness in a computer’s barricade. Anti-virus companies and operating system companies are working to patch weakness in systems and to detect infiltrators. However, with the advance of fragmentation, detection might even prove to be more difficult. Malware detection relies on signatures to identify malware of certain shapes. With fragmentation, functionality and size can change depending on how many fragments are used and how the fragments are created. In this paper we present a robust malware detection technique, with emphasis on detecting fragmentation malware attacks in RFID systems that can be extended to detect complex obfuscated and mutated malware. After a particular fragmented malware has been first identified, it can be analyzed to extract the signature, which provides a basis for detecting variants and mutants of similar types of malware in the future. Encouraging experimental results on a limited set of recent malware are presented.     

Abstracting minimal security-relevant behaviors for malware analysis

Dynamic behavior-based malware analysis and detection is considered to be one of the most promising ways to combat with the obfuscated and unknown malwares. To perform such analysis, behavioral feature abstraction plays a fundamental role, because how to specify program formally to a large extend determines what kind of algorithm can be used. In existing research, graph-based methods keep a dominant position in specifying malware behaviors. However, they restrict the detection algorithm to be chosen from graph mining algorithm. In this paper, we build a complete virtual environment to capture malware behaviors, especially that to stimulate network behaviors of a malware. Then, we study the problem of abstracting constant behavioral features from API call sequences and propose a minimal security-relevant behavior abstraction way, which absorbs the advantages of prevalent graph-based methods in behavior representation and has the following advantages: first API calls are aggregated by data dependence, therefore it is resistent to redundant data and is a kind of more constant feature. Second, API call arguments are also abstracted particularly, this further contributes to common and constant behavioral features of malware variants. Third, it is a moderate degree aggregation of a small group of API calls with a constructing criterion that centering on an independent operation on a sensitive resource. Fourth, it is very easy to embed the extracted behaviors in a high dimensional vector space, so that it can be processed by almost all of the prevalent statistical learning algorithms. We then evaluate these minimal security-relevant behaviors in three kinds of test, including similarity comparison, clustering and classification. The experimental results show that our method has a capacity in distinguishing malwares from different families and also from benign programs, and it is useful for many statistical learning algorithms.     

Titans’ revenge: Detecting Zeus via its own flaws

Malware is one of the main threats to the Internet security in general, and to commercial transactions in particular. However, given the high level of sophistication reached by malware (e.g. usage of encrypted payload and obfuscation techniques), malware detection tools and techniques still call for effective and efficient solutions. In this paper, we address a specific, dreadful, and widely diffused financial malware: Zeus.The contributions of this paper are manifold: first, we propose a technique to break the encrypted malware communications, extracting the keystream used to encrypt such communications; second, we provide a generalization of the proposed keystream extraction technique. Further, we propose Cronus, an IDS that specifically targets Zeus malware. The implementation of Cronus has been experimentally tested on a production network, and its high quality performance and effectiveness are discussed. Finally, we highlight some principles underlying malware—and Zeus in particular—that could pave the way for further investigation in this field.     

基于关键应用编程接口图的恶意代码检测

针对基于特征码的恶意代码检测方法无法应对混淆变形技术的问题,提出基于关键应用编程接口(API)图的检测方法。通过提取恶意代码控制流图中含关键API调用的节点,将恶意行为抽象成关键API图,采用子图匹配的方法判定可疑程序的恶意度。实验结果证明,该方法能有效检测恶意代码变体,漏报率较低。     

Fools Download Where Angels Fear to Tread

Our study illustrates that the risk of getting infected by malware that antivirus protection doesn't detect is alarmingly high. New malware that the antivirus engines don't have signatures for is likely to escape detection by a desktop antivirus solution. Taking precautions while using the Internet can protect users only to a certain extent. If they visit the wrong Web site or download a file infected with 0-day malware, they probably won't be protected from infection. The malware specimens that our antivirus packages didn't detect during our two-week exposure period suggest to us that signature-based antivirus software doesn't provide sufficient protection for users who live on the bleeding edge with respect to where they obtain their software. Coupled with the exponential growth of new malware variants, our findings suggest that antivirus vendors have major problems keeping the signature lag within acceptable limits.