基于异常特征的钓鱼网站URL检测技术

典型的网络钓鱼是采用群发垃圾邮件,欺骗用户点击钓鱼网站URL地址,登录并输入个人机密信息的一种攻击手段。文章通过分析钓鱼网站URL地址的结构和词汇特征,提出一种基于异常特征的钓鱼网站URL检测方法。抽取钓鱼网站URL地址中4个结构特征、8个词汇特征,组成12个特征的特征向量,用SVM进行训练和分类。对PhishTank上7291条钓鱼网站URL分类实验,检测出7134条钓鱼网站URL,准确率达到97.85%。     

基于SVM主动学习算法的网络钓鱼检测系统

针对钓鱼式网络攻击,从URL入手,对网址URL和Web页面内容综合特征进行识别、分类,实现网络钓鱼检测并保证检测的效率和精度.用支持向量机主动学习算法和适合小样本集的分类模型提高分类性能.实验结果证明,网络钓鱼检测系统能达到较高的检测精度.     

A lightweight and proactive rule-based incremental construction approach to detect phishing scam

The development of digitization over the globe has made digital security inescapable. As every single article on this planet is being digitalized quickly, it is more important to protect those items. Numerous cyber threats effectively deceive ordinary individuals to take away their identifications. Phishing is a kind of social engineering attack where the hackers are using this kind of attack in modern days to steal the user's credentials. After a systematic research analysis of phishing technique and email scam, an intrusion detection system in chrome extension is developed. This technique is used to detect real-time phishing by examining the URL, domain, content and page attributes of an URL prevailing in an email and any web page portion. Considering the reliability, robustness and scalability of an efficient phishing detection system, we designed a lightweight and proactive rule-based incremental construction approach to detect any unknown phishing URLs. Due to the computational intelligence and nondependent of the blacklist signatures, this application can detect the zero-day and spear phishing attacks with a detection rate of 89.12% and 76.2%, respectively. The true positive values acquired in our method is 97.13% and it shows less than 1.5% of false positive values. Thus the application shows the precision level higher than the previous model developed and other phishing techniques. The overall results indicate that our framework outperforms the existing method in identifying phishing URLs.

     

一种基于集成学习的钓鱼网站检测方法

针对钓鱼攻击者常用的伪造HTTPS网站以及其他混淆技术,借鉴了目前主流基于机器学习以及规则匹配的检测钓鱼网站的方法RMLR和PhishDef,增加对网页文本关键字和网页子链接等信息进行特征提取的过程,提出了Nmap-RF分类方法。Nmap-RF是基于规则匹配和随机森林方法的集成钓鱼网站检测方法。根据网页协议对网站进行预过滤,若判定其为钓鱼网站则省略后续特征提取步骤。否则以文本关键字置信度,网页子链接置信度,钓鱼类词汇相似度以及网页PageRank作为关键特征,以常见URL、Whois、DNS信息和网页标签信息作为辅助特征,经过随机森林分类模型判断后给出最终的分类结果。实验证明,Nmap-RF集成方法可以在平均9~10 μs的时间内对钓鱼网页进行检测,且可以过滤掉98.4%的不合法页面,平均总精度可达99.6%。     

Predicting phishing websites based on self-structuring neural network

Internet has become an essential component of our everyday social and financial activities. Nevertheless, internet users may be vulnerable to different types of web threats, which may cause financial damages, identity theft, loss of private information, brand reputation damage and loss of customer’s confidence in e-commerce and online banking. Phishing is considered as a form of web threats that is defined as the art of impersonating a website of an honest enterprise aiming to obtain confidential information such as usernames, passwords and social security number. So far, there is no single solution that can capture every phishing attack. In this article, we proposed an intelligent model for predicting phishing attacks based on artificial neural network particularly self-structuring neural networks. Phishing is a continuous problem where features significant in determining the type of web pages are constantly changing. Thus, we need to constantly improve the network structure in order to cope with these changes. Our model solves this problem by automating the process of structuring the network and shows high acceptance for noisy data, fault tolerance and high prediction accuracy. Several experiments were conducted in our research, and the number of epochs differs in each experiment. From the results, we find that all produced structures have high generalization ability.     

A multi-tier phishing detection and filtering approach

Phishing attacks continue to pose serious risks for consumers and businesses as well as threatening global security and the economy. Therefore, developing countermeasures against such attacks is an important step towards defending critical infrastructures such as banking. Although different types of classification algorithms for filtering phishing have been proposed in the literature, the scale and sophistication of phishing attacks have continued to increase steadily. In this paper, we propose a new approach called multi-tier classification model for phishing email filtering. We also propose an innovative method for extracting the features of phishing email based on weighting of message content and message header and select the features according to priority ranking. We will also examine the impact of rescheduling the classifier algorithms in a multi-tier classification process to find out the optimum scheduling. A detailed empirical performance and analysis of the proposed algorithm is present. The results of the experiments show that the proposed algorithm reduces the false positive problems substantially with lower complexity.     

An efficient phishing webpage detector

Phishing attack is growing significantly each year and is considered as one of the most dangerous threats in the Internet which may cause people to lose confidence in e-commerce. In this paper, we present a heuristic method to determine whether a webpage is a legitimate or a phishing page. This scheme could detect new phishing pages which black list based anti-phishing tools could not. We first convert a web page into 12 features which are well selected based on the existing normal and fishing pages. A training set of web pages including normal and fishing pages are then input for a support vector machine to do training. A testing set is finally fed into the trained model to do the testing. Compared to the existing methods, the experimental results show that the proposed phishing detector can achieve the high accuracy rate with relatively low false positive and low false negative rates.     

ISHO: improved spotted hyena optimization algorithm for phishing website detection

One of the major challenges in cyber space and Internet of things (IoT) environments is the existence of fake or phishing websites that steal users’ information. A website as a multimedia system provides access to different types of data such as text, image, video, audio. Each type of these data are prune to be used by fishers to perform a phishing attack. In phishing attacks, people are directed to fake pages and their important information is stolen by a thief or phisher. Machine learning and data mining algorithms are the widely used algorithms for classifying websites and detecting phishing attacks. Classification accuracy is highly dependent on the feature selection method employed to choose appropriate features for classification. In this research, an improved spotted hyena optimization algorithm (ISHO algorithm) is proposed to select proper features for classifying phishing websites through support vector machine. The proposed ISHO algorithm outperformed the standard spotted hyena optimization algorithm with better accuracy. In addition, the results indicate the superiority of ISHO algorithm to three other meta-heuristic algorithms including particle swarm optimization, firefly algorithm, and bat algorithm. The proposed algorithm is also compared with a number of classification algorithms proposed before on the same dataset.

     

基于文本和DNS查询的非常规域名检测研究

在钓鱼网站、远控木马等网络攻击中常使用大量的非常规域名。面对海量域名,已有非常规域名检测方法准确性有待提高。基于对使用非常规域名的网络攻击特征,以及对已有非常规域名检测方法的研究,提出了域名伪装特征,分隔特征域名标签被数字分割的最大单元数,DNS查询特征:单次DNS查询返回的IP个数和DNS查询返回IP集合的平均杰卡德距离;改进了发音特征域名元音字母占比。此外,提出一种基于文本特征和DNS查询特征的非常规域名检测方法,其中选取了新定义的特征,以及若干其他域名基本特征、发音特征和分隔特征,并基于机器学习方法区分常规域名和非常规域名。实验结果表明,提出的非常规域名检测方法与部分已有方法相比准确率有较大提高,可用于检测使用了非常规域名的恶意网络攻击。     

基于集成学习的钓鱼网页深度检测系统

网络钓鱼是一种在线欺诈行为,它利用钓鱼网页仿冒正常合法的网页,窃取用户敏感信息从而达到非法目的.提出了基于集成学习的钓鱼网页深度检测方法,采用网页渲染来应对常见的页面伪装手段,提取渲染后网页的URL信息特征、链接信息特征以及页面文本特征,利用集成学习的方法,针对不同的特征信息构造并训练不同的基础分类器模型,最后利用分类集成策略综合多个基础分类器生成最终的结果.针对PhishTank钓鱼网页的检测实验表明,本文提出的检测方法具有较好的准确率与召回率.     

Detection of phishing attacks in Iranian e-banking using a fuzzy–rough hybrid system

Phishing is a method of stealing electronic identity in which social engineering and website forging methods are used in order to mislead users and reveal confidential information having economic value. Destroying the trust between users in business network, phishing has a negative effect on the budding area of e-commerce. Developing countries such as Iran have been recently facing Internet threats like phishing, whose methods, regarding the social differences, may be different from other experiences. Thus, it is necessary to design a suitable detection method for these deceits. The aim of current paper is to provide a phishing detection system to be used in e-banking system in Iran. Identifying the outstanding features of phishing is one of the important prerequisites in design of an accurate system; therefore, in first step, to identify the influential features of phishing that best fit the Iranian bank sites, a list of 28 phishing indicators was prepared. Using feature selection algorithm based on rough sets theory, six main indicators were identified as the most effective factors. The fuzzy expert system was designed using these indicators, afterwards. The results show that the proposed system is able to determine the Iranian phishing sites with a reasonable speed and precision, having an accuracy of 88%.     

Detecting Phishing Web Pages with Visual Similarity Assessment Based on Earth Mover's Distance (EMD)

An effective approach to phishing Web page detection is proposed, which uses Earth mover's distance (EMD) to measure Web page visual similarity. We first convert the involved Web pages into low resolution images and then use color and coordinate features to represent the image signatures. We use EMD to calculate the signature distances of the images of the Web pages. We train an EMD threshold vector for classifying a Web page as a phishing or a normal one. Large-scale experiments with 10,281 suspected Web pages are carried out to show high classification precision, phishing recall, and applicable time performance for online enterprise solution. We also compare our method with two others to manifest its advantage. We also built up a real system which is already used online and it has caught many real phishing cases     

DoS Attack Detection Based on Deep Factorization Machine in SDN

Software-Defined Network (SDN) decouples the control plane of network devices from the data plane. While alleviating the problems presented in traditional network architectures, it also brings potential security risks, particularly network Denial-of-Service (DoS) attacks. While many research efforts have been devoted to identifying new features for DoS attack detection, detection methods are less accurate in detecting DoS attacks against client hosts due to the high stealth of such attacks. To solve this problem, a new method of DoS attack detection based on Deep Factorization Machine (DeepFM) is proposed in SDN. Firstly, we select the Growth Rate of Max Matched Packets (GRMMP) in SDN as detection feature. Then, the DeepFM algorithm is used to extract features from flow rules and classify them into dense and discrete features to detect DoS attacks. After training, the model can be used to infer whether SDN is under DoS attacks, and a DeepFM-based detection method for DoS attacks against client host is implemented. Simulation results show that our method can effectively detect DoS attacks in SDN. Compared with the K-Nearest Neighbor (K-NN), Artificial Neural Network (ANN) models, Support Vector Machine (SVM) and Random Forest models, our proposed method outperforms in accuracy, precision and F1 values.     

Phish Block: A Blockchain Framework for Phish Detection in Cloud

The data in the cloud is protected by various mechanisms to ensure security aspects and user’s privacy. But, deceptive attacks like phishing might obtain the user’s data and use it for malicious purposes. In Spite of much technological advancement, phishing acts as the first step in a series of attacks. With technological advancements, availability and access to the phishing kits has improved drastically, thus making it an ideal tool for the hackers to execute the attacks. The phishing cases indicate use of foreign characters to disguise the original Uniform Resource Locator (URL), typosquatting the popular domain names, using reserved characters for re directions and multi-chain phishing. Such phishing URLs can be stored as a part of the document and uploaded in the cloud, providing a nudge to hackers in cloud storage. The cloud servers are becoming the trusted tool for executing these attacks. The prevailing software for blacklisting phishing URLs lacks the security for multi-level phishing and expects security from the client’s end (browser). At the same time, the avalanche effect and immutability of block-chain proves to be a strong source of security. Considering these trends in technology, a block-chain based filtering implementation for preserving the integrity of user data stored in the cloud is proposed. The proposed Phish Block detects the homographic phishing URLs with accuracy of 91% which assures the security in cloud storage.     

基于码元高斯拟合的PUE攻击检测策略*

针对仿冒主用户（PUE）恶意干扰并占用有效频段所造成的频谱资源稀缺问题,提出了一种基于高斯函数特征提取的PUE攻击检测方法。在论证码元上包络起伏特征可以作为细微特征提取的基础上,结合高斯拟合,提取出不同用户发射源的特征参数,利用模糊C均值聚类算法来区分主用户与仿冒攻击用户。仿真实验证明,该方法在不同信噪比下所提取出的两辐射源特征差异明显,稳定性高,可靠性好,能够快速有效地检测出PUE攻击用户。     

使用可信计算技术防范网络仿冒攻击

网络仿冒攻击已经成为互联网上最大的安全威胁之一,给金融机构和普通消费者造成了巨大的损失,严重影响了网上银行和电子商务的发展。我们分析了当前网络浏览器存在的安全漏洞,讨论了在线用户验证的问题,并且提出了使用可信计算平台对在线用户验证的方法。这种方法不仅能使很多网络仿冒攻击失效,而且可以防范其他在线攻击。     

Two-stage ELM for phishing Web pages detection using hybrid features

Increasing high volume phishing attacks are being encountered every day due to attackers’ high financial returns. Recently, there has been significant interest in applying machine learning for phishing Web pages detection. Different from literatures, this paper introduces predicted labels of textual contents to be part of the features and proposes a novel framework for phishing Web pages detection using hybrid features consisting of URL-based, Web-based, rule-based and textual content-based features. We achieve this framework by developing an efficient two-stage extreme learning machine (ELM). The first stage is to construct classification models on textual contents of Web pages using ELM. In particular, we take Optical Character Recognition (OCR) as an assistant tool to extract textual contents from image format Web pages in this stage. In the second stage, a classification model on hybrid features is developed by using a linear combination model-based ensemble ELMs (LC-ELMs), with the weights calculated by the generalized inverse. Experimental results indicate the proposed framework is promising for detecting phishing Web pages.     

基于AdaCostBoost算法的网络钓鱼检测

针对日益严重的网络钓鱼攻击, 提出机器学习的方法进行钓鱼网站的检测和判断. 首先, 根据URL提取敏感特征, 然后, 采用AdaBoost算法进行训练出分类器, 再用训练好的分类器对未知URL检测识别. 最后, 针对非平衡代价问题, 采用了改进后的AdaBoost算法--AdaCostBoost, 加入代价因子的计算. 实验结果表明, 文中提出的网络钓鱼检测方法, 具有较优的检测性能.     

Phishing threat avoidance behaviour: An empirical investigation

Phishing is an online identity theft that aims to steal sensitive information such as username, password and online banking details from its victims. Phishing education needs to be considered as a means to combat this threat. This paper reports on a design and development of a mobile game prototype as an educational tool helping computer users to protect themselves against phishing attacks. The elements of a game design framework for avoiding phishing attacks were used to address the game design issues. Our mobile game design aimed to enhance the users' avoidance behaviour through motivation to protect themselves against phishing threats. A think-aloud study was conducted, along with a pre- and post-test, to assess the game design framework though the developed mobile game prototype. The study results showed a significant improvement of participants' phishing avoidance behaviour in their post-test assessment. Furthermore, the study findings suggest that participants' threat perception, safeguard effectiveness, self-efficacy, perceived severity and perceived susceptibility elements positively impact threat avoidance behaviour, whereas safeguard cost had a negative impact on it.