arXiv subjects

David Mohaisen

Publications and source records attributed to David Mohaisen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations

This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance metrics. Our findings, highlighting how prone those techniques are to simple attacks, are alarming, and the inconsistency in the attacks' effect on different algorithms promises ways for attack mitigation. We examine the effectiveness of different mitigation strategies, including adversarial training and enhanced feature selection, in enhancing model robustness and show their effectiveness.

cs.CR↗

arXiv2025

Fishing for Phishers: Learning-Based Phishing Detection in Ethereum Transactions

Phishing detection on Ethereum has increasingly leveraged advanced machine learning techniques to identify fraudulent transactions. However, limited attention has been given to understanding the effectiveness of feature selection strategies and the role of graph-based models in enhancing detection accuracy. In this paper, we systematically examine these issues by analyzing and contrasting explicit transactional features and implicit graph-based features, both experimentally and analytically. We explore how different feature sets impact the performance of phishing detection models, particularly in the context of Ethereum's transactional network. Additionally, we address key challenges such as class imbalance and dataset composition and their influence on the robustness and precision of detection methods. Our findings demonstrate the advantages and limitations of each feature type, while also providing a clearer understanding of how feature affect model resilience and generalization in adversarial environments.

cs.CR↗

arXiv2025

Through the Looking Glass: LLM-Based Analysis of AR/VR Android Applications Privacy Policies

\begin{abstract} This paper comprehensively analyzes privacy policies in AR/VR applications, leveraging BERT, a state-of-the-art text classification model, to evaluate the clarity and thoroughness of these policies. By comparing the privacy policies of AR/VR applications with those of free and premium websites, this study provides a broad perspective on the current state of privacy practices within the AR/VR industry. Our findings indicate that AR/VR applications generally offer a higher percentage of positive segments than free content but lower than premium websites. The analysis of highlighted segments and words revealed that AR/VR applications strategically emphasize critical privacy practices and key terms. This enhances privacy policies' clarity and effectiveness.

cs.CR↗

arXiv2025

Evaluating Large Language Models in Vulnerability Detection Under Variable Context Windows

This study examines the impact of tokenized Java code length on the accuracy and explicitness of ten major LLMs in vulnerability detection. Using chi-square tests and known ground truth, we found inconsistencies across models: some, like GPT-4, Mistral, and Mixtral, showed robustness, while others exhibited a significant link between tokenized length and performance. We recommend future LLM development focus on minimizing the influence of input length for better vulnerability detection. Additionally, preprocessing techniques that reduce token count while preserving code structure could enhance LLM accuracy and explicitness in these tasks.

cs.CR↗

arXiv2025

I Can Find You in Seconds! Leveraging Large Language Models for Code Authorship Attribution

Source code authorship attribution is important in software forensics, plagiarism detection, and protecting software patch integrity. Existing techniques often rely on supervised machine learning, which struggles with generalization across different programming languages and coding styles due to the need for large labeled datasets. Inspired by recent advances in natural language authorship analysis using large language models (LLMs), which have shown exceptional performance without task-specific tuning, this paper explores the use of LLMs for source code authorship attribution. We present a comprehensive study demonstrating that state-of-the-art LLMs can successfully attribute source code authorship across different languages. LLMs can determine whether two code snippets are written by the same author with zero-shot prompting, achieving a Matthews Correlation Coefficient (MCC) of 0.78, and can attribute code authorship from a small set of reference code snippets via few-shot learning, achieving MCC of 0.77. Additionally, LLMs show some adversarial robustness against misattribution attacks. Despite these capabilities, we found that naive prompting of LLMs does not scale well with a large number of authors due to input token limitations. To address this, we propose a tournament-style approach for large-scale attribution. Evaluating this approach on datasets of C++ (500 authors, 26,355 samples) and Java (686 authors, 55,267 samples) code from GitHub, we achieve classification accuracy of up to 65% for C++ and 68.7% for Java using only one reference per author. These results open new possibilities for applying LLMs to code authorship attribution in cybersecurity and software engineering.

cs.SE↗

arXiv2024

Dissecting the Infrastructure Used in Web-based Cryptojacking: A Measurement Perspective

This paper conducts a comprehensive examination of the infrastructure supporting cryptojacking operations. The analysis elucidates the methodologies, frameworks, and technologies malicious entities employ to misuse computational resources for unauthorized cryptocurrency mining. The investigation focuses on identifying websites serving as platforms for cryptojacking activities. A dataset of 887 websites, previously identified as cryptojacking sites, was compiled and analyzed to categorize the attacks and malicious activities observed. The study further delves into the DNS IP addresses, registrars, and name servers associated with hosting these websites to understand their structure and components. Various malware and illicit activities linked to these sites were identified, indicating the presence of unauthorized cryptocurrency mining via compromised sites. The findings highlight the vulnerability of website infrastructures to cryptojacking.

cs.CR↗

arXiv2024

Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis

This paper explores the vulnerability of machine learning models, specifically Random Forest, Decision Tree, and K-Nearest Neighbors, to very simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance metrics, such as accuracy, precision, recall, and F1-score. Our findings, highlighting how prone those techniques are to simple attacks, are alarming, and the inconsistency in the attacks' effect on different algorithms promises ways for attack mitigation. We examine the effectiveness of different mitigation strategies, including adversarial training and enhanced feature selection, in enhancing model robustness.

cs.CR↗

arXiv2023

Understanding the Utilization of Cryptocurrency in the Metaverse and Security Implications

We present our results on analyzing and understanding the behavior and security of various metaverse platforms incorporating cryptocurrencies. We obtained the top metaverse coins with a capitalization of at least 25 million US dollars and the top metaverse domains for the coins, and augmented our data with name registration information (via whois), including the hosting DNS IP addresses, registrant location, registrar URL, DNS service provider, expiry date and check each metaverse website for information on fiat currency for cryptocurrency. The result from virustotal.com includes the communication files, passive DNS, referrer files, and malicious detections for each metaverse domain. Among other insights, we discovered various incidents of malicious detection associated with metaverse websites. Our analysis highlights indicators of (in)security, in the correlation sense, with the files and other attributes that are potentially responsible for the malicious activities.

cs.CR↗

arXiv2023

The Infrastructure Utilization of Free Contents Websites Reveal their Security Characteristics

Free Content Websites (FCWs) are a significant element of the Web, and realizing their use is essential. This study analyzes FCWs worldwide by studying how they correlate with different network sizes, cloud service providers, and countries, depending on the type of content they offer. Additionally, we compare these findings with those of premium content websites (PCWs). Our analysis concluded that FCWs correlate mainly with networks of medium size, which are associated with a higher concentration of malicious websites. Moreover, we found a strong correlation between PCWs, cloud, and country hosting patterns. At the same time, some correlations were also observed concerning FCWs but with distinct patterns contrasting each other for both types. Our investigation contributes to comprehending the FCW ecosystem through correlation analysis, and the indicative results point toward controlling the potential risks caused by these sites through adequate segregation and filtering due to their concentration.

cs.CR↗

arXiv2023

Untargeted Code Authorship Evasion with Seq2Seq Transformation

Code authorship attribution is the problem of identifying authors of programming language codes through the stylistic features in their codes, a topic that recently witnessed significant interest with outstanding performance. In this work, we present SCAE, a code authorship obfuscation technique that leverages a Seq2Seq code transformer called StructCoder. SCAE customizes StructCoder, a system designed initially for function-level code translation from one language to another (e.g., Java to C#), using transfer learning. SCAE improved the efficiency at a slight accuracy degradation compared to existing work. We also reduced the processing time by about 68% while maintaining an 85% transformation success rate and up to 95.77% evasion success rate in the untargeted setting.

cs.CR↗

arXiv2023

Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutations

Toward robust malware detection, we explore the attack surface of existing malware detection systems. We conduct root-cause analyses of the practical binary-level black-box adversarial malware examples. Additionally, we uncover the sensitivity of volatile features within the detection engines and exhibit their exploitability. Highlighting volatile information channels within the software, we introduce three software pre-processing steps to eliminate the attack surface, namely, padding removal, software stripping, and inter-section information resetting. Further, to counter the emerging section injection attacks, we propose a graph-based section-dependent information extraction scheme for software representation. The proposed scheme leverages aggregated information within various sections in the software to enable robust malware detection and mitigate adversarial settings. Our experimental results show that traditional malware detection models are ineffective against adversarial threats. However, the attack surface can be largely reduced by eliminating the volatile information. Therefore, we propose simple-yet-effective methods to mitigate the impacts of binary manipulation attacks. Overall, our graph-based malware detection scheme can accurately detect malware with an area under the curve score of 88.32\% and a score of 88.19% under a combination of binary manipulation attacks, exhibiting the efficiency of our proposed scheme.

cs.LG↗

arXiv2023

Understanding the Country-Level Security of Free Content Websites and their Hosting Infrastructure

This paper examines free content websites (FCWs) and premium content websites (PCWs) in different countries, comparing them to general websites. The focus is on the distribution of malicious websites and their correlation with the national cyber security index (NCSI), which measures a country's cyber security maturity and its ability to deter the hosting of such malicious websites. By analyzing a dataset comprising 1,562 FCWs and PCWs, along with Alexa's top million websites dataset sample, we discovered that a majority of the investigated websites are hosted in the United States. Interestingly, the United States has a relatively low NCSI, mainly due to a lower score in privacy policy development. Similar patterns were observed for other countries With varying NCSI criteria. Furthermore, we present the distribution of various categories of FCWs and PCWs across countries. We identify the top hosting countries for each category and provide the percentage of discovered malicious websites in those countries. Ultimately, the goal of this study is to identify regional vulnerabilities in hosting FCWs and guide policy improvements at the country level to mitigate potential cyber threats.

cs.CR↗

arXiv2023

Analyzing In-browser Cryptojacking

Cryptojacking is the permissionless use of a target device to covertly mine cryptocurrencies. With cryptojacking, attackers use malicious JavaScript codes to force web browsers into solving proof-of-work puzzles, thus making money by exploiting the resources of the website visitors. To understand and counter such attacks, we systematically analyze the static, dynamic, and economic aspects of in-browser cryptojacking. For static analysis, we perform content, currency, and code-based categorization of cryptojacking samples to 1) measure their distribution across websites, 2) highlight their platform affinities, and 3) study their code complexities. We apply machine learning techniques to distinguish cryptojacking scripts from benign and malicious JavaScript samples with 100\% accuracy. For dynamic analysis, we analyze the effect of cryptojacking on critical system resources, such as CPU and battery usage. We also perform web browser fingerprinting to analyze the information exchange between the victim node and the dropzone cryptojacking server. We also build an analytical model to empirically evaluate the feasibility of cryptojacking as an alternative to online advertisement. Our results show a sizeable negative profit and loss gap, indicating that the model is economically infeasible. Finally, leveraging insights from our analyses, we build countermeasures for in-browser cryptojacking that improve the existing remedies.

cs.CR↗

arXiv2023

SHIELD: Thwarting Code Authorship Attribution

Authorship attribution has become increasingly accurate, posing a serious privacy risk for programmers who wish to remain anonymous. In this paper, we introduce SHIELD to examine the robustness of different code authorship attribution approaches against adversarial code examples. We define four attacks on attribution techniques, which include targeted and non-targeted attacks, and realize them using adversarial code perturbation. We experiment with a dataset of 200 programmers from the Google Code Jam competition to validate our methods targeting six state-of-the-art authorship attribution methods that adopt a variety of techniques for extracting authorship traits from source-code, including RNN, CNN, and code stylometry. Our experiments demonstrate the vulnerability of current authorship attribution methods against adversarial attacks. For the non-targeted attack, our experiments demonstrate the vulnerability of current authorship attribution methods against the attack with an attack success rate exceeds 98.5\% accompanied by a degradation of the identification confidence that exceeds 13\%. For the targeted attacks, we show the possibility of impersonating a programmer using targeted-adversarial perturbations with a success rate ranging from 66\% to 88\% for different authorship attribution techniques under several adversarial scenarios.

cs.CR↗

arXiv2023

Understanding the Security and Performance of the Web Presence of Hospitals: A Measurement Study

Using a total of 4,774 hospitals categorized as government, non-profit, and proprietary hospitals, this study provides the first measurement-based analysis of hospitals' websites and connects the findings with data breaches through a correlation analysis. We study the security attributes of three categories, collectively and in contrast, against domain name, content, and SSL certificate-level features. We find that each type of hospital has a distinctive characteristic of its utilization of domain name registrars, top-level domain distribution, and domain creation distribution, as well as content type and HTTP request features. Security-wise, and consistent with the general population of websites, only 1\% of government hospitals utilized DNSSEC, in contrast to 6\% of the proprietary hospitals. Alarmingly, we found that 25\% of the hospitals used plain HTTP, in contrast to 20\% in the general web population. Alarmingly too, we found that 8\%-84\% of the hospitals, depending on their type, had some malicious contents, which are mostly attributed to the lack of maintenance. We conclude with a correlation analysis against 414 confirmed and manually vetted hospitals' data breaches. Among other interesting findings, our study highlights that the security attributes highlighted in our analysis of hospital websites are forming a very strong indicator of their likelihood of being breached. Our analyses are the first step towards understanding patient online privacy, highlighting the lack of basic security in many hospitals' websites and opening various potential research directions.

cs.CR↗

arXiv2022

Learning Location from Shared Elevation Profiles in Fitness Apps: A Privacy Perspective

The extensive use of smartphones and wearable devices has facilitated many useful applications. For example, with Global Positioning System (GPS)-equipped smart and wearable devices, many applications can gather, process, and share rich metadata, such as geolocation, trajectories, elevation, and time. For example, fitness applications, such as Runkeeper and Strava, utilize the information for activity tracking and have recently witnessed a boom in popularity. Those fitness tracker applications have their own web platforms and allow users to share activities on such platforms or even with other social network platforms. To preserve the privacy of users while allowing sharing, several of those platforms may allow users to disclose partial information, such as the elevation profile for an activity, which supposedly would not leak the location of the users. In this work, and as a cautionary tale, we create a proof of concept where we examine the extent to which elevation profiles can be used to predict the location of users. To tackle this problem, we devise three plausible threat settings under which the city or borough of the targets can be predicted. Those threat settings define the amount of information available to the adversary to launch the prediction attacks. Establishing that simple features of elevation profiles, e.g., spectral features, are insufficient, we devise both natural language processing (NLP)-inspired text-like representation and computer vision-inspired image-like representation of elevation profiles, and we convert the problem at hand into text and image classification problem. We use both traditional machine learning- and deep learning-based techniques and achieve a prediction success rate ranging from 59.59\% to 99.80\%. The findings are alarming, highlighting that sharing elevation information may have significant location privacy risks.

cs.CR↗

arXiv2022

Do Content Management Systems Impact the Security of Free Content Websites? A Correlation Analysis

This paper investigates the potential causes of the vulnerabilities of free content websites to address risks and maliciousness. Assembling more than 1,500 websites with free and premium content, we identify their content management system (CMS) and malicious attributes. We use frequency analysis at both the aggregate and per category of content (books, games, movies, music, and software), utilizing the unpatched vulnerabilities, total vulnerabilities, malicious count, and percentiles to uncover trends and affinities of usage and maliciousness of CMS{'s} and their contribution to those websites. Moreover, we find that, despite the significant number of custom code websites, the use of CMS{'s} is pervasive, with varying trends across types and categories. Finally, we find that even a small number of unpatched vulnerabilities in popular CMS{'s} could be a potential cause for significant maliciousness.

cs.CR↗

arXiv2022

Miners in the Cloud: Measuring and Analyzing Cryptocurrency Mining in Public Clouds

Cryptocurrencies, arguably the most prominent application of blockchains, have been on the rise with a wide mainstream acceptance. A central concept in cryptocurrencies is "mining pools", groups of cooperating cryptocurrency miners who agree to share block rewards in proportion to their contributed mining power. Despite many promised benefits of cryptocurrencies, they are equally utilized for malicious activities; e.g., ransomware payments, stealthy command, control, etc. Thus, understanding the interplay between cryptocurrencies, particularly the mining pools, and other essential infrastructure for profiling and modeling is important. In this paper, we study the interplay between mining pools and public clouds by analyzing their communication association through passive domain name system (pDNS) traces. We observe that 24 cloud providers have some association with mining pools as observed from the pDNS query traces, where popular public cloud providers, namely Amazon and Google, have almost 48% of such an association. Moreover, we found that the cloud provider presence and cloud provider-to-mining pool association both exhibit a heavy-tailed distribution, emphasizing an intrinsic preferential attachment model with both mining pools and cloud providers. We measure the security risk and exposure of the cloud providers, as that might aid in understanding the intent of the mining: among the top two cloud providers, we found almost 35% and 30% of their associated endpoints are positively detected to be associated with malicious activities, per the virustotal.com scan. Finally, we found that the mining pools presented in our dataset are predominantly used for mining Metaverse currencies, highlighting a shift in cryptocurrency use, and demonstrating the prevalence of mining using public clouds.

cs.CR↗