Legitimate Websites Research Articles

Auto-essentialization: Gender in automated facial analysis as extended colonial project

Scholars are increasingly concerned about social biases in facial analysis systems, particularly with regard to the tangible consequences of misidentification of marginalized groups. However, few have examined how automated facial analysis technologies intersect with the historical genealogy of racialized gender—the gender binary and its classification as a highly racialized tool of colonial power and control. In this paper, we introduce the concept of auto-essentialization: the use of automated technologies to re-inscribe the essential notions of difference that were established under colonial rule. We consider how the face has emerged as a legitimate site of gender classification, despite being historically tied to projects of racial domination. We examine the history of gendering the face and body, from colonial projects aimed at disciplining bodies which do not fit within the European gender binary, to sexology's role in normalizing that binary, to physiognomic practices that ascribed notions of inferiority to non-European groups and women. We argue that the contemporary auto-essentialization of gender via the face is both racialized and trans-exclusive: it asserts a fixed gender binary and it elevates the white face as the ultimate model of gender difference. We demonstrate that imperialist ideologies are reflected in modern automated facial analysis tools in computer vision through two case studies: (1) commercial gender classification and (2) the security of both small-scale (women-only online platforms) and large-scale (national borders) spaces. Thus, we posit a rethinking of ethical attention to these systems: not as immature and novel, but as mature instantiations of much older technologies.

Phishing Website Detection Based on URL

In today's era, due to the surge in the usage of the internet and other online platforms, security has been major attention. Many cyberattacks take place each day out of which website phishing is the most common issue. It is an act of imitating a legitimate website and thereby tricking the users and stealing their sensitive information. So, concerning this problem, this paper will introduce a possible solution to avoid such attacks by checking whether the provided URLs are phishing URLs or legitimate URLs. It is a Machine Learning based system especially Supervised learning where we have provided 2000 phishing and 2000 legitimate URL dataset. We have taken into consideration the Random Forest Algorithm due to its performance and accuracy. It considers 9 features and hence detects whether the URL is safe to access or a phishing URL.

Phishing websites detection via CNN and multi-head self-attention on imbalanced datasets

Phishing websites belong to a social engineering attack where perpetrators fake legitimate websites to lure people to access so as to illegally acquire user’s identity, password, privacy and even properties. This attack imposes a great threat to people and becomes more and more severe. In order to identify phishing websites, many proposals have shown their merits. For example, the classical proposal CNN-LSTM received a very high precision by combining Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) together. However, despite CNN achieved great success in AI area, LSTM still exists the biases issue since it always treats the later features much more important than the former ones. In the meanwhile, as the self-attention mechanism can discover the text’s inner dependency relationships, it has been widely applied to various tasks of deep learning-based Natural Language Processing (NLP). If we treat a URL as a text string, this mechanism can learn comprehensive URL representations. In order to improve the accuracy for phishing websites detection further, in this paper, we propose a novel Convolutional Neural Network (CNN) with self-attention named self-attention CNN for phishing Uniform Resource Locators (URLs) identification. Specifically, self-attention CNN first leverages Generative Adversarial Network (GAN) to generate phishing URLs so as to balance the datasets of legitimate and phishing URLs. Then it utilizes CNN and multi-head self-attention to construct our new classifier which is comprised of four blocks, namely the input block, the attention block, the feature block and the output block. Finally, the trained classifier can give a high-accuracy result for an unknown website URL. Overall thorough experiments indicate that self-attention CNN achieves 95.6% accuracy, which outperforms CNN-LSTM, single CNN and single LSTM by 1.4%, 4.6% and 2.1% respectively.

An Optimized Stacking Ensemble Model for Phishing Websites Detection

Security attacks on legitimate websites to steal users’ information, known as phishing attacks, have been increasing. This kind of attack does not just affect individuals’ or organisations’ websites. Although several detection methods for phishing websites have been proposed using machine learning, deep learning, and other approaches, their detection accuracy still needs to be enhanced. This paper proposes an optimized stacking ensemble method for phishing website detection. The optimisation was carried out using a genetic algorithm (GA) to tune the parameters of several ensemble machine learning methods, including random forests, AdaBoost, XGBoost, Bagging, GradientBoost, and LightGBM. The optimized classifiers were then ranked, and the best three models were chosen as base classifiers of a stacking ensemble method. The experiments were conducted on three phishing website datasets that consisted of both phishing websites and legitimate websites—the Phishing Websites Data Set from UCI (Dataset 1); Phishing Dataset for Machine Learning from Mendeley (Dataset 2, and Datasets for Phishing Websites Detection from Mendeley (Dataset 3). The experimental results showed an improvement using the optimized stacking ensemble method, where the detection accuracy reached 97.16%, 98.58%, and 97.39% for Dataset 1, Dataset 2, and Dataset 3, respectively.

Detecting Phishing Website Using Machine Learning

A fraud attempt to get sensitive and personal information like password, username, and bank details like credit/debit card details by masking as a reliable organization in electronic communication. The phishing website will appear the same as the legitimate website and directs the user to a page to enter personal details of the user on the fake website. Through machine learning algorithms one can improve the accuracy of the prediction. The proposed method predicts the URL based phishing websites based on features and also gives maximum accuracy. This method uses uniform resource locator (URL) features. We identified features that phishing site URLs contain. The proposed method employs those features for phishing detection. The proposed system predicts the URL based phishing websites with maximum accuracy.

Detection and prevention of Phishing Attacks

Phishing is one amongst the main issues visaged by cyber-world and ends up in monetary losses for each industries and people. Detection of phishing attack with high accuracy has forever been a difficult issue. At present, visual similarities-based techniques square measure terribly helpful for police work phishing websites expeditiously. Phishing web site appearance terribly similar in look to its corresponding legitimate web site to deceive users into basic cognitive process that they are browsing the right web site. Visual similarity primarily based phishing detection techniques utilize the feature set like text content, text format, HTML tags, Cascading sheet (CSS), image, then forth, to form the choice. These approaches compare the suspicious web site with the corresponding legitimate web site by victimisation numerous options and if the similarity is larger than the predefined threshold price then it is declared phishing [2].

Directed adversarial sampling attacks on phishing detection

Phishing websites trick honest users into believing that they interact with a legitimate website and capture sensitive information, such as user names, passwords, credit card numbers, and other personal information. Machine learning is a promising technique to distinguish between phishing and legitimate websites. However, machine learning approaches are susceptible to adversarial learning attacks where a phishing sample can bypass classifiers. Our experiments on publicly available datasets reveal that the phishing detection mechanisms are vulnerable to adversarial learning attacks. We investigate the robustness of machine learning-based phishing detection in the face of adversarial learning attacks. We propose a practical approach to simulate such attacks by generating adversarial samples through direct feature manipulation. To enhance the sample’s success probability, we describe a clustering approach that guides an attacker to select the best possible phishing samples that can bypass the classifier by appearing as legitimate samples. We define the notion of vulnerability level for each dataset that measures the number of features that can be manipulated and the cost for such manipulation. Further, we clustered phishing samples and showed that some clusters of samples are more likely to exhibit higher vulnerability levels than others. This helps an adversary identify the best candidates of phishing samples to generate adversarial samples at a lower cost. Our finding can be used to refine the dataset and develop better learning models to compensate for the weak samples in the training dataset.

An Enhanced Anti-phishing Scheme to Detect Phishing Website

Phishing is a network attack in which attacker generates a replica of current legitimate site to contrivance the users into submitting their personal and sensitive information. A good anti-phishing solution should have rapid access time and rapid detection rate, but most of the existing solutions fail to satisfy it. A new method is proposed to prevent phishing attack which evaluates the URL Characteristics and cross check with the white-list. The proposed method has higher access time and higher detection rate than other methods. Whenever the user opens a website for the first time which is not available in the white-list, the algorithm proposed here examines the webpage using URL characteristics. The experimental results depict the accuracy of proposed method having accuracy of 93.8% with less negative rate.

Intelligent Piracy Site Detection Technique with High Accuracy

Recently, with the diversification of media services and the development of smart devices, users have more opportunities to use digital content, such as movies, dramas, and music; consequently, the size of the copyright market expands simultaneously. However, there are piracy sites that generate revenue by illegal use of copyrighted works. This has led to losses for copyright holders, and the scale of copyrighted works infringed due to the ever-increasing number of piracy sites has increased. To prevent this, government agencies respond to copyright infringement by monitoring piracy sites using online monitoring and countermeasure strategies for infringement. However, the detection and blocking process consumes a significant amount of time when compared to the rate of generating new piracy sites. Hence, online monitoring is less effective. Additionally, given that piracy sites are sophisticated and refined in the same way as legitimate sites, it is necessary to accurately distinguish and block a site that is involved in copyright infringement. Therefore, in this study, we analyze features of piracy sites and based on this analysis, we propose an intelligent detection technique for piracy sites that automatically classifies and detects whether a site is involved in infringement.

Lightweight URL-based phishing detection using natural language processing transformers for mobile devices

Hackers are increasingly launching phishing attacks via SMS and social media. Games and dating apps introduce yet another attack vector. However, current deep learning-based phishing detection applications are not applicable to mobile devices due to the computational burden. We propose a lightweight phishing detection algorithm that distinguishes phishing from legitimate websites solely from URLs to be used in mobile devices. As a baseline performance, we apply Artificial Neural Networks (ANNs) to URL-based and HTML-based website features. A model search results in 15 ANN models with accuracies >96%, comparable to state-of-the-art approaches. Next, we test the performance of deep ANNs on URL-based features only; however, all models perform poorly with the highest accuracy of 86.2%, indicating that URL-based features alone are not adequate to detect phishing websites even with deep ANNs. Since language transformers learn to represent context-dependent text sequences, we hypothesize that they will be able to learn directly from the text in URLs to distinguish between legitimate and malicious websites. We apply two state-of-the-art deep transformers (BERT and ELECTRA) for phishing detection. Testing custom and standard vocabularies, we find that pre-trained transformers available for immediate use (with fine-tuning) outperform the model trained with the custom URL-based vocabulary. Using pre-trained transformers to predict phishing websites from only URLs has four advantages: 1) requires little training time (~8 minutes), 2) is more easily updatable than feature-based approaches because no pre-processing of URLs is required, 3) is safer to use because phishing websites can be predicted without physically visiting the malicious sites and 4) is easily deployable for real-time detection and is applicable to run on mobile devices.

IMDoC: Identification of Malicious Domain Campaigns via DNS and Communicating Files

Cyber attacks have become more sophisticated and frequent over the years. Detecting the components operated during a cyber attack and relating them to a specific threat actor is one of the main challenges facing cyber security systems. Reliable detection of malicious components and identification of the threat actor is imperative to mitigate security issues by Security Operations Center (SOC) analysts. The Domain Name System (DNS) plays a significant role in most cyber attacks observed nowadays in that domains act as a Command and Control (C&C) in coordinated bot network attacks or impersonate legitimate websites in phishing attacks. Thus, DNS analysis has become a popular tool for malicious domain identification. In this collaborative research associating Ben-Gurion University and IBM, we develop a novel algorithm to detect malicious domains and relate them to a specific malware campaign in a large-scale real-data DNS traffic environment, dubbed Identification of Malicious Domain Campaigns (IMDoC) algorithm. Its novelty resides in developing a framework that combines the existence of communicating files for the observed domains and their DNS request patterns in a real production environment. The analysis was conducted on real data from Quad9 (9.9.9.9) DNS recursive resolvers combined with malicious communicating files extracted from VirusTotal, and confirms the strong performance of the algorithm on a real large-scale data production environment.

Hybrid vs Ensemble Classification Models for Phishing Websites

Phishing is an internet crime achieved by imitating a legitimate website of a host in order to steal confidential information. Many researchers have developed phishing classification models that are limited in real-time and computational efficiency. This paper presents an ensemble learning model composed of DTree and NBayes, by STACKING method, with DTree as base learner. The aim is to combine the advantages of simplicity and effectiveness of DTree with the lower complexity time of NBayes. The models were integrated and appraised independently for data training and the probabilities of each class were averaged by their accuracy on the trained data through testing process. The present results of the empirical study on phishing website dataset suggest that the ensemble model significantly outperformed the hybrid model in terms of the measures used. Finally, DTree and STACKING methods showed superior performances compared to the other models.

Detecting the Phishing Attack Using Collaborative Approach and Secure Login through Dynamic Virtual Passwords

User data protection is a major problem in the technical world. To get critical data from people such as bank account, credit card details and passwords, fraudulent people use different techniques for their advantages. Misuse of user credentials affects many industry sectors day by day. The fraudulent practice where more people connected to a network revealing sensitive data of individual, group or a company of legitimate sources called phishing. The aids for the hackers are forged websites and emails which look similar as original. There are different anti-phishing methods are proposed which follows various methods, to protect users against phishing. Proposed technique has detection of phishing at various stages. It contains incoming mail analysis for its feature as well as source. If mail has link to webpage, that cautious webpage is checked for its legitimateness. It is examined by using two methods. For popular sites, webpage content is compared with content of known legitimate site. The second step is to find whether any cautious site is increasingly dependable on any related pages to calculate relationship strength indirectly or directly associated pages. To protect from phishing attacks, these techniques uses virtual passwords for logging into sites.

Phishing website detection using support vector machines and nature-inspired optimization algorithms

Phishing websites are amongst the biggest threats Internet users face today, and existing methods like blacklisting, using SSL certificates, etc. often fail to keep up with the increasing number of threats. This paper aims to utilise different properties of a website URL, and use a machine learning model to classify websites as phishing and non-phishing. These properties include the IP address length, the authenticity of the HTTPs request being sent by the website, usage of pop-up windows to enter data, Server Form Handler status, etc. A Support Vector Machine binary classifier trained on an existing dataset has been used to predict if a website was a legitimate website or not, by finding an optimum hyperplane to separate the two categories. This optimum hyperplane is found with the help of four optimization algorithms, the Bat Algorithm, the Firefly Algorithm, the Grey Wolf Optimiser algorithm and the Whale Optimization Algorithm, which are inspired by various natural phenomena. Amongst the four nature-inspired optimization algorithms, it has been determined that the Grey Wolf Optimiser algorithm’s performance is significantly better than that of the Firefly Algorithm, but there is no significant difference while comparing the performance of any other pair of algorithms. However, all four nature-inspired optimization algorithms perform significantly better than the grid-search optimized Random Forest classifier model described in earlier research.

A comprehensive survey of AI-enabled phishing attacks detection techniques.

In recent times, a phishing attack has become one of the most prominent attacks faced by internet users, governments, and service-providing organizations. In a phishing attack, the attacker(s) collects the client’s sensitive data (i.e., user account login details, credit/debit card numbers, etc.) by using spoofed emails or fake websites. Phishing websites are common entry points of online social engineering attacks, including numerous frauds on the websites. In such types of attacks, the attacker(s) create website pages by copying the behavior of legitimate websites and sends URL(s) to the targeted victims through spam messages, texts, or social networking. To provide a thorough understanding of phishing attack(s), this paper provides a literature review of Artificial Intelligence (AI) techniques: Machine Learning, Deep Learning, Hybrid Learning, and Scenario-based techniques for phishing attack detection. This paper also presents the comparison of different studies detecting the phishing attack for each AI technique and examines the qualities and shortcomings of these methodologies. Furthermore, this paper provides a comprehensive set of current challenges of phishing attacks and future research direction in this domain.

Correlation Impact by Random Forest Towards Prediction of Phishing Website

Phishing is an online identity theft that lure unsuspecting victims into phishing website that asks for their personal information such as financial credentials or online access. The most obvious phishing attacks use spam emails to lure victims into visiting its phishing website. The less obvious attack is when a phisher spoofes legitimate sites to bring the victims to the phishing website by presenting a visually similar websites. To address this issue, this paper focuses on the effectiveness of the Random Forest algorithm in predicting a website whether a phishing or lieitimate website. The prediction model is developed using the classfication methodology and the results revealed that the prediction accuracy of Random Forest in only 66.66%. This is due to potential high correlation among the features when training the dataset since each Random Tree in the forest should protect each other from individual errors. In the future, this project is hoped to investigate features selection of the same dataset because the phishing website prediction model requires features that at least some predictive power.

Risk management and corporate governance failures in Islamic banks: a case study

Purpose The purpose of this paper is to show how the choice and ongoing evaluation of a firm’s business model, as a matter of strategic guidance, are key aspects of corporate governance (CG), with particular reference to risk management (RM) in Islamic banks. Design/methodology/approach This research uses a case study approach, with a single case, which was chosen as it fits very well the purpose of this research. The data collection was based largely on documentary evidence. Company data were collected from company annual reports, press releases and legitimate web sites. The ORBIS Bank Focus database was also used to produce a comparative financial analysis. Findings The study findings illustrate how an apparently successful business model may fail due to an inherent instability that could have been identified through the application of careful risk analysis (including stress testing) in the choice and ongoing evaluation of the business model, which robust CG and strategic guidance require. In particular, Arcapita’s problems illustrate the dangers to Islamic financial institutions (IFI) from business models that involve undue exposure to liquidity risk. Practical implications The issues raised in the paper are important in that Islamic banking and finance is an integral part of the global banking and finance industry. Investors and regulators are now requesting corporate management to provide improved service to shareholders and other stakeholders alike. IFI rely on the confidence of investors and market participants, just like conventional institutions and when this confidence erodes, it may prove difficult to regain. Social implications The global credit crisis of 2008 caused significant difficulties to firms, especially financial institutions, even with substantial government intervention in the economy, which raised some issues of CG and ethics. Originality/value This paper extends the knowledge of the potential effects of weaknesses in CG and RM, with specific reference to strategic guidance in the choice and ongoing evaluation of a firm’s business model, especially in relation to the Islamic banking sector. It also provides a telling illustration of the need for the enhancements of the Basel Committee’s prudential requirements set out in the various Basel III documents.

Analyzing and eliminating phishing threats in IoT, network and other Web applications using iterative intersection

In today’s cyber era, Internet of Things (IoT) based products are increasingly adopted by users for various purposes. Accesses to these systems are facilitated via a web application to the end user. Traditionally, Phishing attacks were targeted toward banking and financial systems. With the rise in usage of IoT, the attack surface increases. Along with IoT specific attacks, attackers are targeting users with Phishing to steal passwords in order to gain access to IoT devices like security cameras. Phishing is an online attack that has been around for more than two decades. Though there are advanced prevention and detection mechanisms designed and developed by researchers and organizations, statistics show that Phishing has been on the rise. Often, there is a monetary incentive for the bad actor that carries out a phishing attack. This motivates attackers to advance their evasion mechanisms and maintain the status quo as a race between detection and evasion. A methodology Phish-Sec was introduced which paves a way to counter Phishing attacks in a pro-active manner by aggregating signatures of legitimate websites at the source. Phish-Sec involves determining uniqueness across ‘n’ websites. This manuscript provides the mathematical solution using intersection to determine the uniqueness of a visited web page. Iterative intersection is incorporated with Phish-sec to facilitate poison avoidance in its back-end system. By this, Phish-Sec can be expanded to a variety of applications, including non-financial based systems like IoT. It is proved that the overall efficiency of Phish-Sec increases along with its expansion capabilities. The true positive achieved by phish-sec is 99.15% which is 0.15% higher.

Pishing Attacks in Network Security

In the last few decays, phishing tricks have swiftly grown posing enormous threat to worldwide Internet security. These days, phishing attacks are one of the utmost common and serious threats over internet whereas cyber attackers are trying to steal users personal information regarding their financial assets by using different malwares and social engineering. The usual way of phishing attacks use some electronic messaging like emails or by providing the links that appears to be legitimate sites but actually these sites are malicious and controlled by the attackers. To detect phishing attack at high accuracy is always a crucial and has been great issue of interest. Recently many detection techniques has been introduced which are specifically designed for the detection of phishing with extreme accuracy. In this report the phishing attacks are discuss with some of the techniques which are proposed in various literature.

Draining the Water Hole: Mitigating Social Engineering Attacks with CyberTWEAK

Cyber adversaries have increasingly leveraged social engineering attacks to breach large organizations and threaten the well-being of today's online users. One clever technique, the “watering hole” attack, compromises a legitimate website to execute drive-by download attacks by redirecting users to another malicious domain. We introduce a game-theoretic model that captures the salient aspects for an organization protecting itself from a watering hole attack by altering the environment information in web traffic so as to deceive the attackers. Our main contributions are (1) a novel Social Engineering Deception (SED) game model that features a continuous action set for the attacker, (2) an in-depth analysis of the SED model to identify computationally feasible real-world cases, and (3) the CyberTWEAK algorithm which solves for the optimal protection policy. To illustrate the potential use of our framework, we built a browser extension based on our algorithms which is now publicly available online. The CyberTWEAK extension will be vital to the continued development and deployment of countermeasures for social engineering.