57 citations · 163 across the 20 of their papers we have counts for
23 papers
PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI
Mohamed Amine Ferrag, Merouane Debbah, Abderrahmane Lakas +2
Recent advances in Physical AI have accelerated the use of foundation models in autonomous systems such as unmanned aerial vehicles (UAVs), which must perceive, reason, plan, and a…
The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution
Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky +2
In this paper, we present the first large-scale study exploring whether JavaScript code generated by Large Language Models (LLMs) can reveal which model produced it, enabling relia…
Sustaining Cyber Awareness: The Long-Term Impact of Continuous Phishing Training and Emotional Triggers
Rebeka Toth, Richard A. Dubniczky, Olga Limonova +1
Phishing constitutes more than 90\% of successful cyberattacks globally, remaining one of the most persistent threats to organizational security. Despite organizations tripling the…
You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models
Richard A. Dubniczky, Bertalan Borsos, Tamas Bisztray +1
The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlooked security risks. Beyond PDFs, these…
I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution
Tamas Bisztray, Bilel Cherif, Richard A. Dubniczky +6
Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identi…
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda +3
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration.…
DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response
Bilel Cherif, Tamas Bisztray, Richard A. Dubniczky +3
Digital Forensics and Incident Response (DFIR) involves analyzing digital evidence to support legal investigations. Large Language Models (LLMs) offer new opportunities in DFIR tas…
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah
Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the g…
CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection
Richard A. Dubniczky, Krisztofer Zoltán Horvát, Tamás Bisztray +3
Identifying vulnerabilities in source code is crucial, especially in critical software components. Existing methods such as static analysis, dynamic analysis, formal verification,…
Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview
Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag +4
Software testing and verification are critical for ensuring the reliability and security of modern software systems. Traditionally, formal verification techniques, such as model ch…
Reasoning Beyond Limits: Advances and Open Problems for LLMs
Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah
Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and…
Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence
Norbert Tihanyi, Tamas Bisztray, Richard A. Dubniczky +11
As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often simplistic, allowing…
Securing Tomorrow's Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies
Ridhi Jain, Norbert Tihanyi, Mohamed Amine Ferrag
Integrating Deep Learning (DL) techniques in the Internet of Vehicles (IoV) introduces many security challenges and issues that require thorough examination. This literature review…
Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
Mohamed Amine Ferrag, Fatima Alwahedi, Ammar Battah +5
This paper provides a comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs). We explore LLM applications across various domains…
How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models
Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag +2
This study compares state-of-the-art Large Language Models (LLMs) on their tendency to generate vulnerabilities when writing C programs using a neutral zero-shot prompt. Tihanyi et…
CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge
Norbert Tihanyi, Mohamed Amine Ferrag, Ridhi Jain +2
Large Language Models (LLMs) are increasingly used across various domains, from software development to cyber threat intelligence. Understanding all the different fields of cyberse…
ESBMC v7.4: Harnessing the Power of Intervals
Rafael Menezes, Mohannad Aldughaim, Bruno Farias +9
ESBMC implements many state-of-the-art techniques for model checking. We report on new and improved features that allow us to obtain verification results for previously unsupported…
SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi +8
Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the mar…
The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification
Norbert Tihanyi, Tamas Bisztray, Ridhi Jain +3
This paper presents the FormAI dataset, a large collection of 112, 000 AI-generated compilable and independent C programs with vulnerability classification. We introduce a dynamic…
Privacy-Preserving Password Cracking: How a Third Party Can Crack Our Password Hash Without Learning the Hash Value or the Cleartext
Norbert Tihanyi, Tamas Bisztray, Bertalan Borsos +1
Using the computational resources of an untrusted third party to crack a password hash can pose a high number of privacy and security risks. The act of revealing the hash digest co…
Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices
Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi +4
The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groun…
Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses
Mohamed Amine Ferrag, Othmane Friha, Burak Kantarci +6
The ongoing deployment of the fifth generation (5G) wireless networks constantly reveals limitations concerning its original concept as a key driver of Internet of Everything (IoE)…
A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
Norbert Tihanyi, Ridhi Jain, Yiannis Charalambous +3
This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially,…