166 citations · 291 across the 36 of their papers we have counts for
41 papers
Detecting Adversarial Images through Response Profiles of Vision-Language Models
Arash Vashagh, Roozbeh Razavi-Far
Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible.…
GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks
Arash Vashagh, Roozbeh Razavi-Far
Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upgraded. Directly transferring…
KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks
Mohammad Meymani, Roozbeh Razavi-Far
While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exposed to adversarial threats. W…
TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems
Refat Ishrak Hemel, Ehsan Hallaji, Roozbeh Razavi-Far
The emergence of metaverse platforms has created virtual economies that introduce new challenges related to fraud, bot activity, and illicit financial behavior. Despite growing int…
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
Alfarizy Alfarizy, Hung Truong Thanh Nguyen, René Richard +2
Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small subset of experts, so the per-token comp…
Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods
Roozbeh Razavi-Far, Mohammad Meymani, Erfan Mahmoudinia +6
Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine lear…
Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval
Hamed Jelodar, Samita Bai, Mohammad Meymani +3
Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured decision-making. Despite rapi…
LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering
Hamed Jelodar, Samita Bai, Tochukwu Emmanuel Nwankwo +4
Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Alt…
Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models
Samita Bai, Hamed Jelodar, Tochukwu Emmanuel Nwankwo +4
Malware family classification remains a challenging task in automated malware analysis, particularly in real-world settings characterized by obfuscation, packing, and rapidly evolv…
Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection
Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins +1
Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph mo…
Transparent Malware Detection With Granular Assembly Flow Explainability via Graph Neural Networks
Griffin Higgins, Roozbeh Razavi-Far, Hossein Shokouhinejad +1
As malware continues to become increasingly sophisticated, threatening, and evasive, malware detection systems must keep pace and become equally intelligent, powerful, and transpar…
LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation
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 syste…
Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Training
Mohammad Meymani, Roozbeh Razavi-Far
Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domain…
Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation
Parisa Hamedi, Hamed Jelodar, Samita Bai +3
Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language mode…
A Research and Development Portfolio of GNN Centric Malware Detection, Explainability, and Dataset Curation
Hossein Shokouhinejad, Griffin Higgins, Roozbeh Razavi-Far +1
Graph Neural Networks (GNNs) have become an effective tool for malware detection by capturing program execution through graph-structured representations. However, important challen…
Can Small GenAI Language Models Rival Large Language Models in Understanding Application Behavior?
Mohammad Meymani, Hamed Jelodar, Parisa Hamedi +2
Generative AI (GenAI) models, particularly large language models (LLMs), have transformed multiple domains, including natural language processing, software analysis, and code under…
SBAN: A Framework & Multi-Dimensional Dataset for Large Language Model Pre-Training and Software Code Mining
Hamed Jelodar, Mohammad Meymani, Samita Bai +2
This paper introduces SBAN (Source code, Binary, Assembly, and Natural Language Description), a large-scale, multi-dimensional dataset designed to advance the pre-training and eval…
FlexiDataGen: An Adaptive LLM Framework for Dynamic Semantic Dataset Generation in Sensitive Domains
Hamed Jelodar, Samita Bai, Roozbeh Razavi-Far +1
Dataset availability and quality remain critical challenges in machine learning, especially in domains where data are scarce, expensive to acquire, or constrained by privacy regula…
XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security
Hamed Jelodar, Mohammad Meymani, Roozbeh Razavi-Far +1
Generative AI and large language models (LLMs) have shown strong capabilities in code understanding, but their use in cybersecurity, particularly for malware detection and analysis…
NLD-LLM: A systematic framework for evaluating small language transformer models on natural language description
Hamed Jelodar, Mohammad Meymani, Parisa Hamedi +4
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 t…
Explainable Attention-Guided Stacked Graph Neural Networks for Malware Detection
Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins +1
Malware detection in modern computing environments demands models that are not only accurate but also interpretable and robust to evasive techniques. Graph neural networks (GNNs) h…
A Study on Semi-Supervised Detection of DDoS Attacks under Class Imbalance
Ehsan Hallaji, Vaishnavi Shanmugam, Roozbeh Razavi-Far +1
One of the most difficult challenges in cybersecurity is eliminating Distributed Denial of Service (DDoS) attacks. Automating this task using artificial intelligence is a complex p…
Dual Explanations via Subgraph Matching for Malware Detection
Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins +1
Interpretable malware detection is crucial for understanding harmful behaviors and building trust in automated security systems. Traditional explainable methods for Graph Neural Ne…
Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery
Alireza Fathalizadeh, Roozbeh Razavi-Far
Continual generalized category discovery has been introduced and studied in the literature as a method that aims to continuously discover and learn novel categories in incoming dat…