The problem of detecting phishing emails through machine learning techniques has been discussed extensively in the literature. Conventional and state-of-the-art machine learning algorithms have demonstrated the possibility of building classifiers with high accuracy. The existing research studies treat phishing and genuine emails through general indicators and thus it is not exactly clear what phishing features are contributing to variations of the classifiers. In this paper, we crafted a set of phishing and legitimate emails with similar indicators in order to investigate whether these cues are captured or disregarded by email embeddings, i.e., vectorizations. We then fed machine learning classifiers with the carefully crafted emails to find out about the performance of email embeddings developed. Our results show that using these indicators, email embeddings techniques is effective for classifying emails as phishing or legitimate.
University of Tokyo（东京大学）；United Nations University（联合国大学）
With increasingly more sophisticated phishing campaigns in recent years, phishing emails lure people using more legitimate-looking personal contexts. To tackle this problem, instead of traditional heuristics-based algorithms, more adaptive detection systems such as natural language processing (NLP)-powered approaches are essential to understanding phishing text representations. Nevertheless, concerns surrounding the collection of phishing data that might cover confidential information hinder the effectiveness of model learning. We propose a decentralized phishing email detection framework call…
Cyber-phishing attacks recently became more precise, targeted, and tailored by training data to activate only in the presence of specific information or cues. They are adaptable to a much greater extent than traditional phishing detection. Hence, automated detection systems cannot always be 100% accurate, increasing the uncertainty around expected behavior when faced with a potential phishing email. On the other hand, human-centric defence approaches focus extensively on user training but face the difficulty of keeping users up to date with continuously emerging patterns. Therefore, advances i…
Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；Cyber Security Cooperative Research Centre（网络安全合作研究中心）
The use of Artificial Intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which opens it up to a myriad of privacy, trust, and legal issues. Moreover, organizations are loathed to share emails, given the risk of leakage of commercially sensitive information. So, it is uncommon to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly Federated Learning (FL), is a desideratum. Already prevalent in the healthcare sector, questions remain regar…
University of New South Wales（新南威尔士大学）；Cybersecurity CRC（网络安全合作研究中心）；CSIRO’s Data61（联邦科学与工业研究组织Data61研究所）
Email phishing has become more prevalent and grows more sophisticated over time. To combat this rise, many machine learning (ML) algorithms for detecting phishing emails have been developed. However, due to the limited email data sets on which these algorithms train, they are not adept at recognising varied attacks and, thus, suffer from concept drift; attackers can introduce small changes in the statistical characteristics of their emails or websites to successfully bypass detection. Over time, a gap develops between the reported accuracy from literature and the algorithm's actual effectivene…
Phishing is a kind of attack in which criminals use spoofed emails and fraudulent web sites to trick financial organization and customers. Criminals try to lure online users by convincing them to reveal the username, passwords, credit card number and updating account information or fill billing information.
Nebulon Enterprise Simulated Threats for Phishing Research (NEST-Phish): A Synthetic Enterprise Phishing Email Dataset for Behavioral and Machine-Learning Research
We examined the influence of three social engineering strategies on users' judgments of how safe it is to click on a link in an email. The three strategies examined were authority, scarcity and social proof, and the emails were either genuine, phishing or spear-phishing. Of the three strategies, the use of authority was the most effective strategy in convincing users that a link in an email was safe. When detecting phishing and spear-phishing emails, users performed the worst when the emails used the authority principle and performed best when social proof was present. Overall, users struggled…
Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems
Department of Computer Science, School of Mathematics, Computer Science and Engineering, City St George’s, University of London, UK（伦敦大学城市学院计算机科学系，数学、计算机科学与工程学院，伦敦大学）
An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach
Department of Computer Science and Engineering, BGC Trust University Bangladesh（Bangladesh BGC Trust 大学 计算机科学与工程系）；Department of Computer Science and Engineering, International Islamic University Chittagong（Bangladesh 国际伊斯兰大学 昌德加荣分校 计算机科学与工程系）；Centre for Securing Digital Futures, School of Science, Edith Cowan University（澳大利亚 埃德温·考文大学 科学学院 安全数字未来中心）
Edith Cowan University（伊迪丝·考恩大学）；Cybersecurity Cooperative Research Centre（网络安全合作研究中心）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61研究所）；Charles Sturt University（查尔斯史都华大学）；The University of Sydney（悉尼大学）；The Alan Turing Institute（艾伦·图灵研究所）
Spear Phishing is a harmful cyber-attack facing business and individuals worldwide. Considerable research has been conducted recently into the use of Machine Learning (ML) techniques to detect spear-phishing emails. ML-based solutions may suffer from zero-day attacks; unseen attacks unaccounted for in the training data. As new attacks emerge, classifiers trained on older data are unable to detect these new varieties of attacks resulting in increasingly inaccurate predictions. Spear Phishing detection also faces scalability challenges due to the growth of the required features which is proporti…
Despite sophisticated phishing email detection systems, and training and awareness programs, humans continue to be tricked by phishing emails. In an attempt to better understand why phishing email attacks still work and how best to mitigate them, we have carried out an empirical study to investigate people's thought processes when reading their emails. We used a scenario-based role-play "think aloud" method and follow-up interviews to collect data from 19 participants. The experiment was conducted using a simulated web email client, and real phishing and legitimate emails adapted to the given …
Email is a channel of communication which is considered to be a confidential medium of communication for exchange of information among individuals and organisations. The confidentiality consideration about e-mail is no longer the case as attackers send malicious emails to users to deceive them into disclosing their private personal information such as username, password, and bank card details, etc. In search of a solution to combat phishing cybercrime attacks, different approaches have been developed. However, the traditional exiting solutions have been limited in assisting email users to iden…
Phishing attacks are one of the trending cyber attacks that apply socially engineered messages that are communicated to people from professional hackers aiming at fooling users to reveal their sensitive information, the most popular communication channel to those messages is through users emails. This paper presents an intelligent classification model for detecting phishing emails using knowledge discovery, data mining and text processing techniques. This paper introduces the concept of phishing terms weighting which evaluates the weight of phishing terms in each email. The pre processing phas…
This paper examines the cues that typically differentiate phishing emails from genuine emails. The research is conducted in two stages. In the first stage, we identify the cues that actually differentiate between phishing and genuine emails. These are the consistency and personalisation of the message, the perceived legitimacy of links and sender, and the presence of spelling or grammatical irregularities. In the second stage, we identify the cues that participants use to differentiate between phishing and genuine emails. This revealed that participants often use cues that are not good indicat…
In this research, we aim to explore the potential of natural language models (NLMs) such as GPT-3 and GPT-2 to generate effective phishing emails. Phishing emails are fraudulent messages that aim to trick individuals into revealing sensitive information or taking actions that benefit the attackers. We propose a framework for evaluating the performance of NLMs in generating these types of emails based on various criteria, including the quality of the generated text, the ability to bypass spam filters, and the success rate of tricking individuals. Our evaluations show that NLMs are capable of ge…
EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
People’s Liberation Army 77606 Unit（中国人民解放军77606单位）；Field Engineering College, Army Engineering University of PLA（陆军工程大学工程学院）；College Of Software, ZhengZhou University of Light Industry（郑州轻工业大学软件学院）
Most research into anti-phishing defence assumes that the mal-actor is attempting to harvest end-users' personally identifiable information or login credentials and, hence, focuses on detecting phishing websites. The defences for this type of attack are usually activated after the end-user clicks on a link, at which point the link is checked. This is known as after-the-click detection. However, more sophisticated phishing attacks (such as spear-phishing and whaling) are rarely designed to get the end-user to visit a website. Instead, they attempt to get the end-user to perform some other actio…
University of North Dakota（北达科他大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Phishing attacks are one of the most common social engineering attacks targeting users emails to fraudulently steal confidential and sensitive information. They can be used as a part of more massive attacks launched to gain a foothold in corporate or government networks. Over the last decade, a number of anti-phishing techniques have been proposed to detect and mitigate these attacks. However, they are still inefficient and inaccurate. Thus, there is a great need for efficient and accurate detection techniques to cope with these attacks. In this paper, we proposed a phishing attack detection t…
Canadian Institute for Cybersecurity（加拿大网络安全研究所）；University of New Brunswick（新不伦瑞克大学）
Anomalies in emails such as phishing and spam present major security risks such as the loss of privacy, money, and brand reputation to both individuals and organizations. Previous studies on email anomaly detection relied on a single type of anomaly and the analysis of the email body and subject content. A drawback of this approach is that it takes into account the written language of the email content. To overcome this deficit, this study conducted feature extraction and selection on email header datasets and leveraged both multi and one-class anomaly detection approaches. Experimental analys…
The email system is the central battleground against phishing and social engineering attacks, and yet email providers still face key challenges to authenticate incoming emails. As a result, attackers can apply spoofing techniques to impersonate a trusted entity to conduct highly deceptive phishing attacks. In this work, we study email spoofing to answer three key questions: (1) How do email providers detect and handle forged emails? (2) Under what conditions can forged emails penetrate the defense to reach user inbox? (3) Once the forged email gets in, how email providers warn users? Is the wa…
In this paper, we present findings from a large-scale and long-term phishing experiment that we conducted in collaboration with a partner company. Our experiment ran for 15 months during which time more than 14,000 study participants (employees of the company) received different simulated phishing emails in their normal working context. We also deployed a reporting button to the company's email client which allowed the participants to report suspicious emails they received. We measured click rates for phishing emails, dangerous actions such as submitting credentials, and reported suspicious em…
We present the first large-scale characterization of lateral phishing attacks, based on a dataset of 113 million employee-sent emails from 92 enterprise organizations. In a lateral phishing attack, adversaries leverage a compromised enterprise account to send phishing emails to other users, benefitting from both the implicit trust and the information in the hijacked user's account. We develop a classifier that finds hundreds of real-world lateral phishing emails, while generating under four false positives per every one-million employee-sent emails. Drawing on the attacks we detect, as well as…
University of Oxford（牛津大学）；University of Kent（肯特大学）
The emergence of online services in our daily lives has been accompanied by a range of malicious attempts to trick individuals into performing undesired actions, often to the benefit of the adversary. The most popular medium of these attempts is phishing attacks, particularly through emails and websites. In order to defend against such attacks, there is an urgent need for automated mechanisms to identify this malevolent content before it reaches users. Machine learning techniques have gradually become the standard for such classification problems. However, identifying common measurable feature…
Hanoi University of Science and Technology（河内科技大学）；New York University（纽约大学）；University of Oregon（俄勒冈大学）
Anti-phishing aims to detect phishing content/documents in a pool of textual data. This is an important problem in cybersecurity that can help to guard users from fraudulent information. Natural language processing (NLP) offers a natural solution for this problem as it is capable of analyzing the textual content to perform intelligent recognition. In this work, we investigate state-of-the-art techniques for text categorization in NLP to address the problem of anti-phishing for emails (i.e, predicting if an email is phishing or not). These techniques are based on deep learning models that have …
Looking at today phishing panorama, we are able to identify two diametrically opposed approaches. On the one hand, massive phishing targets as many people as possible with generic and preformed texts. On the other hand, spear phishing targets high-value victims with hand-crafted emails. While nowadays these two worlds partially intersect, we envision a future where Natural Language Generation (NLG) techniques will enable attackers to target populous communities with machine-tailored emails. In this paper, we introduce what we call Community Targeted Phishing (CTP), alongside with some workflow…
