Hamed Jelodar

Hamed Jelodar, Samita Bai, Mohammad Meymani et al.

Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured decision-making. Despite rapid advances, there remains limited clarity regarding when, why, where, and what types of graph-LLM integrations are most appropriate across applications. This survey provides a concise, structured overview of the design choices underlying the integration of graphs with LLMs. We categorize existing methods based on their purpose (reasoning, retrieval, generation, recommendation), graph modality (knowledge graphs, scene graphs, interaction graphs, causal graphs, dependency graphs), and integration strategies (prompting, augmentation, training, or agent-based use). By mapping representative works across domains such as cybersecurity, healthcare, materials science, finance, robotics, and multimodal environments, we highlight the strengths, limitations, and best-fit scenarios for each technique. This survey aims to offer researchers a practical guide for selecting the most suitable graph-LLM approach depending on task requirements, data characteristics, and reasoning complexity.

Hamed Jelodar, Samita Bai, Parisa Hamedi et al.

Large Language Models (LLMs) have recently emerged as powerful tools in cybersecurity, offering advanced capabilities in malware detection, generation, and real-time monitoring. Numerous studies have explored their application in cybersecurity, demonstrating their effectiveness in identifying novel malware variants, analyzing malicious code structures, and enhancing automated threat analysis. Several transformer-based architectures and LLM-driven models have been proposed to improve malware analysis, leveraging semantic and structural insights to recognize malicious intent more accurately. This study presents a comprehensive review of LLM-based approaches in malware code analysis, summarizing recent advancements, trends, and methodologies. We examine notable scholarly works to map the research landscape, identify key challenges, and highlight emerging innovations in LLM-driven cybersecurity. Additionally, we emphasize the role of static analysis in malware detection, introduce notable datasets and specialized LLM models, and discuss essential datasets supporting automated malware research. This study serves as a valuable resource for researchers and cybersecurity professionals, offering insights into LLM-powered malware detection and defence strategies while outlining future directions for strengthening cybersecurity resilience.

Hamed Jelodar, Mohammad Meymani, Roozbeh Razavi-Far

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing efficiency, accuracy, and automation. This paper explores the role of LLMs for different code analysis tasks, focusing on three key aspects: 1) what they can analyze and their applications, 2) what models are used and 3) what datasets are used, and the challenges they face. Regarding the goal of this research, we investigate scholarly articles that explore the use of LLMs for source code analysis to uncover research developments, current trends, and the intellectual structure of this emerging field. Additionally, we summarize limitations and highlight essential tools, datasets, and key challenges, which could be valuable for future work.

Hamed Jelodar, Samita Bai, Tochukwu Emmanuel Nwankwo et al.

Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models (LLMs) have shown promise in translating low-level representations into high-level source code, most existing approaches rely on generic code pretraining and lack adaptation to malicious software. We propose LLM4CodeRE, a domain-adaptive LLM framework for bidirectional code reverse engineering that supports both assembly-to-source decompilation and source-to-assembly translation within a unified model. To enable effective task adaptation, we introduce two complementary fine-tuning strategies: (i) a Multi-Adapter approach for task-specific syntactic and semantic alignment, and (ii) a Seq2Seq Unified approach using task-conditioned prefixes to enforce end-to-end generation constraints. Experimental results demonstrate that LLM4CodeRE outperforms existing decompilation tools and general-purpose code models, achieving robust bidirectional generalization.

Samita Bai, Hamed Jelodar, Tochukwu Emmanuel Nwankwo et al.

Malware family classification remains a challenging task in automated malware analysis, particularly in real-world settings characterized by obfuscation, packing, and rapidly evolving threats. Existing machine learning and deep learning approaches typically depend on labeled datasets, handcrafted features, supervised training, or dynamic analysis, which limits their scalability and effectiveness in open-world scenarios. This paper presents a zero-label malware family classification framework based on a weighted hierarchical ensemble of pretrained large language models (LLMs). Rather than relying on feature-level learning or model retraining, the proposed approach aggregates decision-level predictions from multiple LLMs with complementary reasoning strengths. Model outputs are weighted using empirically derived macro-F1 scores and organized hierarchically, first resolving coarse-grained malicious behavior before assigning fine-grained malware families. This structure enhances robustness, reduces individual model instability, and aligns with analyst-style reasoning.

Hamed Jelodar, Mohammad Meymani, Parisa Hamedi et al.

Natural Language Description (NLD) is a Natural Language Processing (NLP) task that requires models to generate structured and meaningful outputs from natural language inputs. In this work, we propose NLD-LLM, a systematic NLP framework to evaluate the performance of language models to generate accurate and concise source code descriptions. This framework incorporates a diverse set of transformer models, including Qwen, DeepSeek, Phi, LLaMA, and Mistral, spanning various sizes, architectures, and training approaches. Central to NLD-LLM is a comprehensive prompt design strategy that includes standardized formatting, clear task guidance, and NLD prompting, ensuring fair and consistent evaluation. Additionally, we apply an iterative refinement process to improve output's quality and assess the model's adaptability. Using semantic and structural metrics, our analysis demonstrates that prompt engineering significantly impacts the effectiveness of the model such that smaller models often performing competitively when supported by well-crafted prompts.

Luis Lazo, Hamed Jelodar, Roozbeh Razavi-Far

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we demonstrate how latent model behaviors can be influenced in unexpected ways. Our experiments encompassed 15,732 prompts, including 10,000 high-priority cases, across LLama, Deepseek, KIMI for code generation, and Claude to verify. The results reveal critical insights into current LLM safeguards, highlighting the need for more robust defense mechanisms, reliable detection strategies, and improved resilience. Importantly, this work provides a principled framework for analyzing and mitigating potential weaknesses, with the goal of advancing safe, responsible, and trustworthy AI technologies.

Parisa Hamedi, Hamed Jelodar, Samita Bai et al.

Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language models on this problem remain scarce. In this work, we present the first comprehensive evaluation of five state-of-the-art large language models on assembly-to-source translation. We assess model performance using a diverse set of metrics capturing lexical similarity (BLEU, ROUGE, and METEOR), semantic alignment (BERTScore), fluency (Perplexity), and efficiency (time prediction). Our results reveal clear trade-offs: while certain models excel in text similarity metrics, others demonstrate lower perplexity or faster inference times. We further provide qualitative analyses of typical model successes and failure cases, highlighting challenges such as control flow recovery and identifier reconstruction. Taken together, our benchmark offers actionable insights into the strengths and limitations of current large language models for program translation, establishing a foundation for future research in combining accuracy with efficiency for real-world applications.

Hamed Jelodar, Samita Bai, Roozbeh Razavi-Far et al.

Dataset availability and quality remain critical challenges in machine learning, especially in domains where data are scarce, expensive to acquire, or constrained by privacy regulations. Fields such as healthcare, biomedical research, and cybersecurity frequently encounter high data acquisition costs, limited access to annotated data, and the rarity or sensitivity of key events. These issues-collectively referred to as the dataset challenge-hinder the development of accurate and generalizable machine learning models in such high-stakes domains. To address this, we introduce FlexiDataGen, an adaptive large language model (LLM) framework designed for dynamic semantic dataset generation in sensitive domains. FlexiDataGen autonomously synthesizes rich, semantically coherent, and linguistically diverse datasets tailored to specialized fields. The framework integrates four core components: (1) syntactic-semantic analysis, (2) retrieval-augmented generation, (3) dynamic element injection, and (4) iterative paraphrasing with semantic validation. Together, these components ensure the generation of high-quality, domain-relevant data. Experimental results show that FlexiDataGen effectively alleviates data shortages and annotation bottlenecks, enabling scalable and accurate machine learning model development.

Hamed Jelodar, Richard Frank

Online forums provide a unique opportunity for online users to share comments and exchange information on a particular topic. Understanding user behaviour is valuable to organizations and has applications for social and security strategies, for instance, identifying user opinions within a community or predicting future behaviour. Discovering the semantic aspects in Incel forums are the main goal of this research; we apply Natural language processing techniques based on topic modeling to latent topic discovery and opinion mining of users from a popular online Incel discussion forum. To prepare the input data for our study, we extracted the comments from Incels.co. The research experiments show that Artificial Intelligence (AI) based on NLP models can be effective for semantic and emotion knowledge discovery and retrieval of useful information from the Incel community. For example, we discovered semantic-related words that describe issues within a large volume of Incel comments, which is difficult with manual methods.

Hamed Jelodar, Rita Orji, Stan Matwin et al.

Taking advantage of social media platforms, such as Twitter, this paper provides an effective framework for emotion detection among those who are quarantined. Early detection of emotional feelings and their trends help implement timely intervention strategies. Given the limitations of medical diagnosis of early emotional change signs during the quarantine period, artificial intelligence models provide effective mechanisms in uncovering early signs, symptoms and escalating trends. Novelty of the approach presented herein is a multitask methodological framework of text data processing, implemented as a pipeline for meaningful emotion detection and analysis, based on the Plutchik/Ekman approach to emotion detection and trend detection. We present an evaluation of the framework and a pilot system. Results of confirm the effectiveness of the proposed framework for topic trends and emotion detection of COVID-19 tweets. Our findings revealed Stay-At-Home restrictions result in people expressing on twitter both negative and positive emotional semantics. Semantic trends of safety issues related to staying at home rapidly decreased within the 28 days and also negative feelings related to friends dying and quarantined life increased in some days. These findings have potential to impact public health policy decisions through monitoring trends of emotional feelings of those who are quarantined. The framework presented here has potential to assist in such monitoring by using as an online emotion detection tool kit.

Hamed Jelodar, Yongli Wang, Rita Orji et al.

Internet forums and public social media, such as online healthcare forums, provide a convenient channel for users (people/patients) concerned about health issues to discuss and share information with each other. In late December 2019, an outbreak of a novel coronavirus (infection from which results in the disease named COVID-19) was reported, and, due to the rapid spread of the virus in other parts of the world, the World Health Organization declared a state of emergency. In this paper, we used automated extraction of COVID-19 related discussions from social media and a natural language process (NLP) method based on topic modeling to uncover various issues related to COVID-19 from public opinions. Moreover, we also investigate how to use LSTM recurrent neural network for sentiment classification of COVID-19 comments. Our findings shed light on the importance of using public opinions and suitable computational techniques to understand issues surrounding COVID-19 and to guide related decision-making.

Hamed Jelodar, Yongli Wang, Mahdi Rabbani et al.

Today, Internet is one of the widest available media worldwide. Recommendation systems are increasingly being used in various applications such as movie recommendation, mobile recommendation, article recommendation and etc. Collaborative Filtering (CF) and Content-Based (CB) are Well-known techniques for building recommendation systems. Topic modeling based on LDA, is a powerful technique for semantic mining and perform topic extraction. In the past few years, many articles have been published based on LDA technique for building recommendation systems. In this paper, we present taxonomy of recommendation systems and applications based on LDA. In addition, we utilize LDA and Gibbs sampling algorithms to evaluate ISWC and WWW conference publications in computer science. Our study suggest that the recommendation systems based on LDA could be effective in building smart recommendation system in online communities.

Hamed Jelodar, Yongli Wang, Mahdi Rabbani et al.

Recommendation systems have an important place to help online users in the internet society. Recommendation Systems in computer science are of very practical use these days in various aspects of the Internet portals, such as social networks, and library websites. There are several approaches to implement recommendation systems, Latent Dirichlet Allocation (LDA) is one the popular techniques in Topic Modeling. Recently, researchers have proposed many approaches based on Recommendation Systems and LDA. According to importance of the subject, in this paper we discover the trends of the topics and find relationship between LDA topics and Scholar-Context-documents. In fact, We apply probabilistic topic modeling based on Gibbs sampling algorithms for a semantic mining from six conference publications in computer science from DBLP dataset. According to our experimental results, our semantic framework can be effective to help organizations to better organize these conferences and cover future research topics.

Hamed Jelodar, Yongli Wang, Chi Yuan et al.

Web spam is a big problem for search engine users in World Wide Web. They use deceptive techniques to achieve high rankings. Although many researchers have presented the different approach for classification and web spam detection still it is an open issue in computer science. Analyzing and evaluating these websites can be an effective step for discovering and categorizing the features of these websites. There are several methods and algorithms for detecting those websites, such as decision tree algorithm. In this paper, we present a systematic framework based on CHAID algorithm and a modified string matching algorithm (KMP) for extract features and analysis of these websites. We evaluated our model and other methods with a dataset of Alexa Top 500 Global Sites and Bing search engine results in 500 queries.

Hamed Jelodar, Yongli Wang, Chi Yuan et al.

Topic modeling is one of the most powerful techniques in text mining for data mining, latent data discovery, and finding relationships among data, text documents. Researchers have published many articles in the field of topic modeling and applied in various fields such as software engineering, political science, medical and linguistic science, etc. There are various methods for topic modeling, which Latent Dirichlet allocation (LDA) is one of the most popular methods in this field. Researchers have proposed various models based on the LDA in topic modeling. According to previous work, this paper can be very useful and valuable for introducing LDA approaches in topic modeling. In this paper, we investigated scholarly articles highly (between 2003 to 2016) related to Topic Modeling based on LDA to discover the research development, current trends and intellectual structure of topic modeling. Also, we summarize challenges and introduce famous tools and datasets in topic modeling based on LDA.