Rakesh Verma

Bryan E. Tuck, Rakesh M. Verma

The rapid development of large language models (LLMs) has significantly improved the generation of fluent and convincing text, raising concerns about their potential misuse on social media platforms. We present a comprehensive methodology for creating nine Twitter datasets to examine the generative capabilities of four prominent LLMs: Llama 3, Mistral, Qwen2, and GPT4o. These datasets encompass four censored and five uncensored model configurations, including 7B and 8B parameter base-instruction models of the three open-source LLMs. Additionally, we perform a data quality analysis to assess the characteristics of textual outputs from human, "censored," and "uncensored" models, employing semantic meaning, lexical richness, structural patterns, content characteristics, and detector performance metrics to identify differences and similarities. Our evaluation demonstrates that "uncensored" models significantly undermine the effectiveness of automated detection methods. This study addresses a critical gap by exploring smaller open-source models and the ramifications of "uncensoring," providing valuable insights into how domain adaptation and content moderation strategies influence both the detectability and structural characteristics of machine-generated text.

Rakesh M. Verma, Nachum Dershowitz, Victor Zeng et al.

Internet-based economies and societies are drowning in deceptive attacks. These attacks take many forms, such as fake news, phishing, and job scams, which we call ``domains of deception.'' Machine-learning and natural-language-processing researchers have been attempting to ameliorate this precarious situation by designing domain-specific detectors. Only a few recent works have considered domain-independent deception. We collect these disparate threads of research and investigate domain-independent deception. First, we provide a new computational definition of deception and break down deception into a new taxonomy. Then, we analyze the debate on linguistic cues for deception and supply guidelines for systematic reviews. Finally, we investigate common linguistic features and give evidence for knowledge transfer across different forms of deception.

Dainis Boumber, Rakesh M. Verma, Fatima Zahra Qachfar

Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. With the globalization of online interactions, individuals are communicating in multiple languages and mixing languages on social media, with varied data becoming available in each language and dialect. At the same time, the techniques for detecting deception are similar across the board. Recent studies have shown the possibility of the existence of universal linguistic cues to deception across domains within the English language; however, the existence of such cues in other languages remains unknown. Furthermore, the practical task of deception detection in low-resource languages is not a well-studied problem due to the lack of labeled data. Another dimension of deception is multimodality. For example, a picture with an altered caption in fake news or disinformation may exist. This paper calls for a comprehensive investigation into the complexities of deceptive language across linguistic boundaries and modalities within the realm of computer security and natural language processing and the possibility of using multilingual transformer models and labeled data in various languages to universally address the task of deception detection.

Bryan E. Tuck, Rakesh M. Verma

Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining. We introduce Representation Stability (RS), a model-agnostic detection framework that identifies adversarial examples by measuring how embedding representations change when important words are masked. RS first ranks words using importance heuristics, then measures embedding sensitivity to masking top-k critical words, and processes the resulting patterns with a BiLSTM detector. Experiments show that adversarially perturbed words exhibit disproportionately high masking sensitivity compared to naturally important words. Across three datasets, three attack types, and two victim models, RS achieves over 88% detection accuracy and demonstrates competitive performance compared to existing state-of-the-art methods, often at lower computational cost. Using Normalized Discounted Cumulative Gain (NDCG) to measure perturbation identification quality, we reveal that gradient-based ranking outperforms attention and random selection approaches, with identification quality correlating with detection performance for word-level attacks. RS also generalizes well to unseen datasets, attacks, and models without retraining, providing a practical solution for adversarial text detection.

Vu Minh Hoang Dang, Rakesh M. Verma

Linguistic richness is essential for advancing natural language processing (NLP), as dataset characteristics often directly influence model performance. However, traditional metrics such as Type-Token Ratio (TTR), Vocabulary Diversity (VOCD), and Measure of Lexical Text Diversity (MTLD) do not adequately capture contextual relationships, semantic richness, and structural complexity. In this paper, we introduce an autoencoder-based framework that uses neural network capacity as a proxy for vocabulary richness, diversity, and complexity, enabling a dynamic assessment of the interplay between vocabulary size, sentence structure, and contextual depth. We validate our approach on two distinct datasets: the DIFrauD dataset, which spans multiple domains of deceptive and fraudulent text, and the Project Gutenberg dataset, representing diverse languages, genres, and historical periods. Experimental results highlight the robustness and adaptability of our method, offering practical guidance for dataset curation and NLP model design. By enhancing traditional vocabulary evaluation, our work fosters the development of more context-aware, linguistically adaptive NLP systems.

Rakesh M. Verma, Nachum Dershowitz

We show the fraught side of the academic publishing realm and illustrate it through a recent case study with an NLP journal.

Fatima Zahra Qachfar, Rakesh M. Verma

We examine the impact of homograph attacks on the Sentiment Analysis (SA) task of different Arabic dialects from the Maghreb North-African countries. Homograph attacks result in a 65.3% decrease in transformer classification from an F1-score of 0.95 to 0.33 when data is written in "Arabizi". The goal of this study is to highlight LLMs weaknesses' and to prioritize ethical and responsible Machine Learning.

Shahryar Baki, Rakesh Verma

Several previous studies have investigated user susceptibility to phishing attacks. A thorough meta-analysis or systematic review is required to gain a better understanding of these findings and to assess the strength of evidence for phishing susceptibility of a subpopulation, e.g., older users. We aim to determine whether an effect exists; another aim is to determine whether the effect is positive or negative and to obtain a single summary estimate of the effect. OBJECTIVES: We systematically review the results of previous user studies on phishing susceptibility and conduct a meta-analysis. METHOD: We searched four online databases for English studies on phishing. We included all user studies in phishing detection and prevention, whether they proposed new training techniques or analyzed users' vulnerability. FINDINGS: A careful analysis reveals some discrepancies between the findings. More than half of the studies that analyzed the effect of age reported no statistically significant relationship between age and users' performance. Some studies reported older people performed better while some reported the opposite. A similar finding holds for the gender difference. The meta-analysis shows: 1) a significant relationship between participants' age and their susceptibility 2) females are more susceptible than males 3) users training significantly improves their detection ability

Amartya Hatua, Arjun Mukherjee, Rakesh M. Verma

This article describes research on claim verification carried out using a multiple GAN-based model. The proposed model consists of three pairs of generators and discriminators. The generator and discriminator pairs are responsible for generating synthetic data for supported and refuted claims and claim labels. A theoretical discussion about the proposed model is provided to validate the equilibrium state of the model. The proposed model is applied to the FEVER dataset, and a pre-trained language model is used for the input text data. The synthetically generated data helps to gain information which helps the model to perform better than state of the art models and other standard classifiers.

Daniel Lee, Rakesh Verma, Avisha Das et al.

In this paper, we revisit the challenging problem of unsupervised single-document summarization and study the following aspects: Integer linear programming (ILP) based algorithms, Parameterized normalization of term and sentence scores, and Title-driven approaches for summarization. We describe a new framework, NewsSumm, that includes many existing and new approaches for summarization including ILP and title-driven approaches. NewsSumm's flexibility allows to combine different algorithms and sentence scoring schemes seamlessly. Our results combining sentence scoring with ILP and normalization are in contrast to previous work on this topic, showing the importance of a broader search for optimal parameters. We also show that the new title-driven reduction idea leads to improvement in performance for both unsupervised and supervised approaches considered.

Avisha Das, Rakesh M. Verma

Advanced machine learning and natural language techniques enable attackers to launch sophisticated and targeted social engineering-based attacks. To counter the active attacker issue, researchers have since resorted to proactive methods of detection. Email masquerading using targeted emails to fool the victim is an advanced attack method. However automatic text generation requires controlling the context and coherency of the generated content, which has been identified as an increasingly difficult problem. The method used leverages a hierarchical deep neural model which uses a learned representation of the sentences in the input document to generate structured written emails. We demonstrate the generation of short and targeted text messages using the deep model. The global coherency of the synthesized text is evaluated using a qualitative study as well as multiple quantitative measures.

Shahryar Baki, Rakesh M. Verma, Arjun Mukherjee et al.

Cyber attacks such as phishing, IRS scams, etc., still are successful in fooling Internet users. Users are the last line of defense against these attacks since attackers seem to always find a way to bypass security systems. Understanding users' reason about the scams and frauds can help security providers to improve users security hygiene practices. In this work, we study the users' reasoning and the effectiveness of several variables within the context of the company representative fraud. Some of the variables that we study are: 1) the effect of using LinkedIn as a medium for delivering the phishing message instead of using email, 2) the effectiveness of natural language generation techniques in generating phishing emails, and 3) how some simple customizations, e.g., adding sender's contact info to the email, affect participants perception. The results obtained from the within-subject study show that participants are not prepared even for a well-known attack - company representative fraud. Findings include: approximately 65% mean detection rate and insights into how the success rate changes with the facade and correspondent (sender/receiver) information. A significant finding is that a smaller set of well-chosen strategies is better than a large `mess' of strategies. We also find significant differences in how males and females approach the same company representative fraud. Insights from our work could help defenders in developing better strategies to evaluate their defenses and in devising better training strategies.

Avisha Das, Shahryar Baki, Ayman El Aassal et al.

Phishing and spear-phishing are typical examples of masquerade attacks since trust is built up through impersonation for the attack to succeed. Given the prevalence of these attacks, considerable research has been conducted on these problems along multiple dimensions. We reexamine the existing research on phishing and spear-phishing from the perspective of the unique needs of the security domain, which we call security challenges: real-time detection, active attacker, dataset quality and base-rate fallacy. We explain these challenges and then survey the existing phishing/spear phishing solutions in their light. This viewpoint consolidates the literature and illuminates several opportunities for improving existing solutions. We organize the existing literature based on detection techniques for different attack vectors (e.g., URLs, websites, emails) along with studies on user awareness. For detection techniques, we examine properties of the dataset, feature extraction, detection algorithms used, and performance evaluation metrics. This work can help guide the development of more effective defenses for phishing, spear-phishing, and email masquerade attacks of the future, as well as provide a framework for a thorough evaluation and comparison.

Samaneh Karimi, Azadeh Shakery, Rakesh Verma

News media websites are important online resources that have drawn great attention of text mining researchers. The main aim of this study is to propose a framework for ranking online news websites from different viewpoints. The ranking of news websites is useful information, which can benefit many news-related tasks such as news retrieval and news recommendation. In the proposed framework, the ranking of news websites is obtained by calculating three measures introduced in the paper and based on user-generated content. Each proposed measure is concerned with the performance of news websites from a particular viewpoint including the completeness of news reports, the diversity of events being covered by the website and its speed. The use of user-generated content in this framework, as a partly-unbiased, real-time and low cost content on the web distinguishes the proposed news website ranking framework from the literature. The results obtained for three prominent news websites, BBC, CNN, NYTimes, show that BBC has the best performance in terms of news completeness and speed, and NYTimes has the best diversity in comparison with the other two websites.

Avisha Das, Rakesh Verma

With an increasing number of malicious attacks, the number of people and organizations falling prey to social engineering attacks is proliferating. Despite considerable research in mitigation systems, attackers continually improve their modus operandi by using sophisticated machine learning, natural language processing techniques with an intent to launch successful targeted attacks aimed at deceiving detection mechanisms as well as the victims. We propose a system for advanced email masquerading attacks using Natural Language Generation (NLG) techniques. Using legitimate as well as an influx of varying malicious content, the proposed deep learning system generates \textit{fake} emails with malicious content, customized depending on the attacker's intent. The system leverages Recurrent Neural Networks (RNNs) for automated text generation. We also focus on the performance of the generated emails in defeating statistical detectors, and compare and analyze the emails using a proposed baseline.

Rakesh Verma, Samaneh Karimi, Daniel Lee et al.

In a disaster situation, first responders need to quickly acquire situational awareness and prioritize response based on the need, resources available and impact. Can they do this based on digital media such as Twitter alone, or newswire alone, or some combination of the two? We examine this question in the context of the 2015 Nepal Earthquakes. Because newswire articles are longer, effective summaries can be helpful in saving time yet giving key content. We evaluate the effectiveness of several unsupervised summarization techniques in capturing key content. We propose a method to link tweets written by the public and newswire articles, so that we can compare their key characteristics: timeliness, whether tweets appear earlier than their corresponding news articles, and content. A novel idea is to view relevant tweets as a summary of the matching news article and evaluate these summaries. Whenever possible, we present both quantitative and qualitative evaluations. One of our main findings is that tweets and newswire articles provide complementary perspectives that form a holistic view of the disaster situation.

Alan T. Sherman, Linda Oliva, Enis Golaszewski et al.

For two days in February 2018, 17 cybersecurity educators and professionals from government and industry met in a "hackathon" to refine existing draft multiple-choice test items, and to create new ones, for a Cybersecurity Concept Inventory (CCI) and Cybersecurity Curriculum Assessment (CCA) being developed as part of the Cybersecurity Assessment Tools (CATS) Project. We report on the results of the CATS Hackathon, discussing the methods we used to develop test items, highlighting the evolution of a sample test item through this process, and offering suggestions to others who may wish to organize similar hackathons. Each test item embodies a scenario, question stem, and five answer choices. During the Hackathon, participants organized into teams to (1) Generate new scenarios and question stems, (2) Extend CCI items into CCA items, and generate new answer choices for new scenarios and stems, and (3) Review and refine draft CCA test items. The CATS Project provides rigorous evidence-based instruments for assessing and evaluating educational practices; these instruments can help identify pedagogies and content that are effective in teaching cybersecurity. The CCI measures how well students understand basic concepts in cybersecurity---especially adversarial thinking---after a first course in the field. The CCA measures how well students understand core concepts after completing a full cybersecurity curriculum.

Luis Moraes, Shahryar Baki, Rakesh Verma et al.

The CL-SciSumm 2016 shared task introduced an interesting problem: given a document D and a piece of text that cites D, how do we identify the text spans of D being referenced by the piece of text? The shared task provided the first annotated dataset for studying this problem. We present an analysis of our continued work in improving our system's performance on this task. We demonstrate how topic models and word embeddings can be used to surpass the previously best performing system.

Rakesh Verma, Daniel Lee

Due to its promise to alleviate information overload, text summarization has attracted the attention of many researchers. However, it has remained a serious challenge. Here, we first prove empirical limits on the recall (and F1-scores) of extractive summarizers on the DUC datasets under ROUGE evaluation for both the single-document and multi-document summarization tasks. Next we define the concept of compressibility of a document and present a new model of summarization, which generalizes existing models in the literature and integrates several dimensions of the summarization, viz., abstractive versus extractive, single versus multi-document, and syntactic versus semantic. Finally, we examine some new and existing single-document summarization algorithms in a single framework and compare with state of the art summarizers on DUC data.

Alan Sherman, M. Dark, A. Chan et al.

Since fall 2012, several National Centers of Academic Excellence in Cyber Defense Research (CAE-Rs) fielded a collaborative course to engage students in solving applied cybersecurity research problems. We describe our experiences with this Information Security Research and Education (INSuRE) research collaborative. We explain how we conducted our project-based research course, give examples of student projects, and discuss the outcomes and lessons learned.