Norbert Tihanyi

Norbert Tihanyi, Tamas Bisztray, Ridhi Jain et al.

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 zero-shot prompting technique constructed to spawn diverse programs utilizing Large Language Models (LLMs). The dataset is generated by GPT-3.5-turbo and comprises programs with varying levels of complexity. Some programs handle complicated tasks like network management, table games, or encryption, while others deal with simpler tasks like string manipulation. Every program is labeled with the vulnerabilities found within the source code, indicating the type, line number, and vulnerable function name. This is accomplished by employing a formal verification method using the Efficient SMT-based Bounded Model Checker (ESBMC), which uses model checking, abstract interpretation, constraint programming, and satisfiability modulo theories to reason over safety/security properties in programs. This approach definitively detects vulnerabilities and offers a formal model known as a counterexample, thus eliminating the possibility of generating false positive reports. We have associated the identified vulnerabilities with Common Weakness Enumeration (CWE) numbers. We make the source code available for the 112, 000 programs, accompanied by a separate file containing the vulnerabilities detected in each program, making the dataset ideal for training LLMs and machine learning algorithms. Our study unveiled that according to ESBMC, 51.24% of the programs generated by GPT-3.5 contained vulnerabilities, thereby presenting considerable risks to software safety and security.

Mohamed Amine Ferrag, Mthandazo Ndhlovu, Norbert Tihanyi et al.

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 groundbreaking Transformer architectures. As the frequency and diversity of cybersecurity attacks continue to rise, the importance of incident detection has significantly increased. IoT devices are expanding rapidly, resulting in a growing need for efficient techniques to autonomously identify network-based attacks in IoT networks with both high precision and minimal computational requirements. This paper presents SecurityBERT, a novel architecture that leverages the Bidirectional Encoder Representations from Transformers (BERT) model for cyber threat detection in IoT networks. During the training of SecurityBERT, we incorporated a novel privacy-preserving encoding technique called Privacy-Preserving Fixed-Length Encoding (PPFLE). We effectively represented network traffic data in a structured format by combining PPFLE with the Byte-level Byte-Pair Encoder (BBPE) Tokenizer. Our research demonstrates that SecurityBERT outperforms traditional Machine Learning (ML) and Deep Learning (DL) methods, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), in cyber threat detection. Employing the Edge-IIoTset cybersecurity dataset, our experimental analysis shows that SecurityBERT achieved an impressive 98.2% overall accuracy in identifying fourteen distinct attack types, surpassing previous records set by hybrid solutions such as GAN-Transformer-based architectures and CNN-LSTM models. With an inference time of less than 0.15 seconds on an average CPU and a compact model size of just 16.7MB, SecurityBERT is ideally suited for real-life traffic analysis and a suitable choice for deployment on resource-constrained IoT devices.

Mohamed Amine Ferrag, Ammar Battah, Norbert Tihanyi et al.

Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications and systems. Traditional bug-fixing methods, such as static analysis, often produce false positives. While bounded model checking, a form of Formal Verification (FV), can provide more accurate outcomes compared to static analyzers, it demands substantial resources and significantly hinders developer productivity. Can Machine Learning (ML) achieve accuracy comparable to FV methods and be used in popular instant code completion frameworks in near real-time? In this paper, we introduce SecureFalcon, an innovative model architecture with only 121 million parameters derived from the Falcon-40B model and explicitly tailored for classifying software vulnerabilities. To achieve the best performance, we trained our model using two datasets, namely the FormAI dataset and the FalconVulnDB. The FalconVulnDB is a combination of recent public datasets, namely the SySeVR framework, Draper VDISC, Bigvul, Diversevul, SARD Juliet, and ReVeal datasets. These datasets contain the top 25 most dangerous software weaknesses, such as CWE-119, CWE-120, CWE-476, CWE-122, CWE-190, CWE-121, CWE-78, CWE-787, CWE-20, and CWE-762. SecureFalcon achieves 94% accuracy in binary classification and up to 92% in multiclassification, with instant CPU inference times. It outperforms existing models such as BERT, RoBERTa, CodeBERT, and traditional ML algorithms, promising to push the boundaries of software vulnerability detection and instant code completion frameworks.

Tamas Bisztray, Bilel Cherif, Richard A. Dubniczky et al.

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, identifying the specific model behind each sample is increasingly important. This paper presents the first systematic study of LLM authorship attribution for C programs. We released CodeT5-Authorship, a novel model that uses only the encoder layers from the original CodeT5 encoder-decoder architecture, discarding the decoder to focus on classification. Our model's encoder output (first token) is passed through a two-layer classification head with GELU activation and dropout, producing a probability distribution over possible authors. To evaluate our approach, we introduce LLM-AuthorBench, a benchmark of 32,000 compilable C programs generated by eight state-of-the-art LLMs across diverse tasks. We compare our model to seven traditional ML classifiers and eight fine-tuned transformer models, including BERT, RoBERTa, CodeBERT, ModernBERT, DistilBERT, DeBERTa-V3, Longformer, and LoRA-fine-tuned Qwen2-1.5B. In binary classification, our model achieves 97.56% accuracy in distinguishing C programs generated by closely related models such as GPT-4.1 and GPT-4o, and 95.40% accuracy for multi-class attribution among five leading LLMs (Gemini 2.5 Flash, Claude 3.5 Haiku, GPT-4.1, Llama 3.3, and DeepSeek-V3). To support open science, we release the CodeT5-Authorship architecture, the LLM-AuthorBench benchmark, and all relevant Google Colab scripts on GitHub: https://github.com/LLMauthorbench/.

Norbert Tihanyi, Mohamed Amine Ferrag, Ridhi Jain et al.

Large Language Models (LLMs) are increasingly used across various domains, from software development to cyber threat intelligence. Understanding all the different fields of cybersecurity, which includes topics such as cryptography, reverse engineering, and risk assessment, poses a challenge even for human experts. To accurately test the general knowledge of LLMs in cybersecurity, the research community needs a diverse, accurate, and up-to-date dataset. To address this gap, we present CyberMetric-80, CyberMetric-500, CyberMetric-2000, and CyberMetric-10000, which are multiple-choice Q&A benchmark datasets comprising 80, 500, 2000, and 10,000 questions respectively. By utilizing GPT-3.5 and Retrieval-Augmented Generation (RAG), we collected documents, including NIST standards, research papers, publicly accessible books, RFCs, and other publications in the cybersecurity domain, to generate questions, each with four possible answers. The results underwent several rounds of error checking and refinement. Human experts invested over 200 hours validating the questions and solutions to ensure their accuracy and relevance, and to filter out any questions unrelated to cybersecurity. We have evaluated and compared 25 state-of-the-art LLM models on the CyberMetric datasets. In addition to our primary goal of evaluating LLMs, we involved 30 human participants to solve CyberMetric-80 in a closed-book scenario. The results can serve as a reference for comparing the general cybersecurity knowledge of humans and LLMs. The findings revealed that GPT-4o, GPT-4-turbo, Mixtral-8x7B-Instruct, Falcon-180B-Chat, and GEMINI-pro 1.0 were the best-performing LLMs. Additionally, the top LLMs were more accurate than humans on CyberMetric-80, although highly experienced human experts still outperformed small models such as Llama-3-8B, Phi-2 or Gemma-7b.

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. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments. Furthermore, we review AI-agent frameworks introduced between 2023 and 2025 that integrate large language models with modular toolkits to enable autonomous decision-making and multi-step reasoning. Moreover, we present real-world applications of autonomous AI agents in materials science, biomedical research, academic ideation, software engineering, synthetic data generation, chemical reasoning, mathematical problem-solving, geographic information systems, multimedia, healthcare, and finance. We then survey key agent-to-agent collaboration protocols, namely the Agent Communication Protocol (ACP), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A). Finally, we discuss recommendations for future research, focusing on advanced reasoning strategies, failure modes in multi-agent LLM systems, automated scientific discovery, dynamic tool integration via reinforcement learning, integrated search capabilities, and security vulnerabilities in agent protocols.

Mohamed Amine Ferrag, Fatima Alwahedi, Ammar Battah et al.

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, including hardware design security, intrusion detection, software engineering, design verification, cyber threat intelligence, malware detection, and phishing detection. We present an overview of LLM evolution and its current state, focusing on advancements in models such as GPT-4, GPT-3.5, Mixtral-8x7B, BERT, Falcon2, and LLaMA. Our analysis extends to LLM vulnerabilities, such as prompt injection, insecure output handling, data poisoning, DDoS attacks, and adversarial instructions. We delve into mitigation strategies to protect these models, providing a comprehensive look at potential attack scenarios and prevention techniques. Furthermore, we evaluate the performance of 42 LLM models in cybersecurity knowledge and hardware security, highlighting their strengths and weaknesses. We thoroughly evaluate cybersecurity datasets for LLM training and testing, covering the lifecycle from data creation to usage and identifying gaps for future research. In addition, we review new strategies for leveraging LLMs, including techniques like Half-Quadratic Quantization (HQQ), Reinforcement Learning with Human Feedback (RLHF), Direct Preference Optimization (DPO), Quantized Low-Rank Adapters (QLoRA), and Retrieval-Augmented Generation (RAG). These insights aim to enhance real-time cybersecurity defenses and improve the sophistication of LLM applications in threat detection and response. Our paper provides a foundational understanding and strategic direction for integrating LLMs into future cybersecurity frameworks, emphasizing innovation and robust model deployment to safeguard against evolving cyber threats.

Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag et al.

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 al. introduced the FormAI dataset at PROMISE'23, featuring 112,000 C programs generated by GPT-3.5-turbo, with over 51.24% identified as vulnerable. We extended that research with a large-scale study involving 9 state-of-the-art models such as OpenAI's GPT-4o-mini, Google's Gemini Pro 1.0, TII's 180 billion-parameter Falcon, Meta's 13 billion-parameter Code Llama, and several other compact models. Additionally, we introduce the FormAI-v2 dataset, which comprises 331 000 compilable C programs generated by these LLMs. Each program in the dataset is labeled based on the vulnerabilities detected in its source code through formal verification, using the Efficient SMT-based Context-Bounded Model Checker (ESBMC). This technique minimizes false positives by providing a counterexample for the specific vulnerability and reduces false negatives by thoroughly completing the verification process. Our study reveals that at least 62.07% of the generated programs are vulnerable. The differences between the models are minor, as they all show similar coding errors with slight variations. Our research highlights that while LLMs offer promising capabilities for code generation, deploying their output in a production environment requires proper risk assessment and validation.

Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah

Recent generative reasoning breakthroughs have transformed how large language models (LLMs) tackle complex problems by dynamically retrieving and refining information while generating coherent, multi-step thought processes. Techniques such as inference-time scaling, reinforcement learning, supervised fine-tuning, and distillation have been successfully applied to models like DeepSeek-R1, OpenAI's o1 & o3, GPT-4o, Qwen-32B, and various Llama variants, resulting in enhanced reasoning capabilities. In this paper, we provide a comprehensive analysis of the top 27 LLM models released between 2023 and 2025 (including models such as Mistral AI Small 3 24B, DeepSeek-R1, Search-o1, QwQ-32B, and phi-4). Then, we present an extensive overview of training methodologies that spans general training approaches, mixture-of-experts (MoE) and architectural innovations, retrieval-augmented generation (RAG), chain-of-thought and self-improvement techniques, as well as test-time compute scaling, distillation, and reinforcement learning (RL) methods. Finally, we discuss the key challenges in advancing LLM capabilities, including improving multi-step reasoning without human supervision, overcoming limitations in chained tasks, balancing structured prompts with flexibility, and enhancing long-context retrieval and external tool integration.

Norbert Tihanyi, Tamas Bisztray, Richard A. Dubniczky et al.

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 models to perform uniformly well and making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs that the models might memorize or guess. To address these limitations, we introduce Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying dataset, DIA-Bench, contains a diverse collection of challenge templates with mutable parameters presented in various formats, including text, PDFs, compiled binaries, visual puzzles, and CTF-style cybersecurity challenges. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, API models like GPT-4o often overestimated their mathematical capabilities, while ChatGPT-4o demonstrated better performance due to effective tool usage. In self-assessment, OpenAI's o1-mini proved to have the best judgement on what tasks it should attempt to solve. We evaluated 25 state-of-the-art LLMs using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its limitations. The dataset is publicly available on the project's page: https://github.com/DIA-Bench.

Mohamed Amine Ferrag, Norbert Tihanyi, Djallel Hamouda et al.

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces have dramatically expanded capabilities for real-time data retrieval, complex computation, and multi-step orchestration. Yet, the explosive proliferation of plugins, connectors, and inter-agent protocols has outpaced discovery mechanisms and security practices, resulting in brittle integrations vulnerable to diverse threats. In this survey, we introduce the first unified, end-to-end threat model for LLM-agent ecosystems, spanning host-to-tool and agent-to-agent communications, formalize adversary capabilities and attacker objectives, and catalog over thirty attack techniques. Specifically, we organized the threat model into four domains: Input Manipulation (e.g., prompt injections, long-context hijacks, multimodal adversarial inputs), Model Compromise (e.g., prompt- and parameter-level backdoors, composite and encrypted multi-backdoors, poisoning strategies), System and Privacy Attacks (e.g., speculative side-channels, membership inference, retrieval poisoning, social-engineering simulations), and Protocol Vulnerabilities (e.g., exploits in Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent Network Protocol (ANP), and Agent-to-Agent (A2A) protocol). For each category, we review representative scenarios, assess real-world feasibility, and evaluate existing defenses. Building on our threat taxonomy, we identify key open challenges and future research directions, such as securing MCP deployments through dynamic trust management and cryptographic provenance tracking; designing and hardening Agentic Web Interfaces; and achieving resilience in multi-agent and federated environments. Our work provides a comprehensive reference to guide the design of robust defense mechanisms and establish best practices for resilient LLM-agent workflows.

Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag et al.

Software testing and verification are critical for ensuring the reliability and security of modern software systems. Traditionally, formal verification techniques, such as model checking and theorem proving, have provided rigorous frameworks for detecting bugs and vulnerabilities. However, these methods often face scalability challenges when applied to complex, real-world programs. Recently, the advent of Large Language Models (LLMs) has introduced a new paradigm for software analysis, leveraging their ability to understand insecure coding practices. Although LLMs demonstrate promising capabilities in tasks such as bug prediction and invariant generation, they lack the formal guarantees of classical methods. This paper presents a comprehensive study of state-of-the-art software testing and verification, focusing on three key approaches: classical formal methods, LLM-based analysis, and emerging hybrid techniques, which combine their strengths. We explore each approach's strengths, limitations, and practical applications, highlighting the potential of hybrid systems to address the weaknesses of standalone methods. We analyze whether integrating formal rigor with LLM-driven insights can enhance the effectiveness and scalability of software verification, exploring their viability as a pathway toward more robust and adaptive testing frameworks.

Richard A. Dubniczky, Krisztofer Zoltán Horvát, Tamás Bisztray et al.

Identifying vulnerabilities in source code is crucial, especially in critical software components. Existing methods such as static analysis, dynamic analysis, formal verification, and recently Large Language Models are widely used to detect security flaws. This paper introduces CASTLE (CWE Automated Security Testing and Low-Level Evaluation), a benchmarking framework for evaluating the vulnerability detection capabilities of different methods. We assess 13 static analysis tools, 10 LLMs, and 2 formal verification tools using a hand-crafted dataset of 250 micro-benchmark programs covering 25 common CWEs. We propose the CASTLE Score, a novel evaluation metric to ensure fair comparison. Our results reveal key differences: ESBMC (a formal verification tool) minimizes false positives but struggles with vulnerabilities beyond model checking, such as weak cryptography or SQL injection. Static analyzers suffer from high false positives, increasing manual validation efforts for developers. LLMs perform exceptionally well in the CASTLE dataset when identifying vulnerabilities in small code snippets. However, their accuracy declines, and hallucinations increase as the code size grows. These results suggest that LLMs could play a pivotal role in future security solutions, particularly within code completion frameworks, where they can provide real-time guidance to prevent vulnerabilities. The dataset is accessible at https://github.com/CASTLE-Benchmark.

Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky et al.

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 reliable authorship attribution and model fingerprinting. With the rapid rise of AI-generated code, attribution is playing a critical role in detecting vulnerabilities, flagging malicious content, and ensuring accountability. While AI-vs-human detection usually treats AI as a single category we show that individual LLMs leave unique stylistic signatures, even among models belonging to the same family or parameter size. To this end, we introduce LLM-NodeJS, a dataset of 50,000 Node.js back-end programs from 20 large language models. Each has four transformed variants, yielding 250,000 unique JavaScript samples and two additional representations (JSIR and AST) for diverse research applications. Using this dataset, we benchmark traditional machine learning classifiers against fine-tuned Transformer encoders and introduce CodeT5-JSA, a custom architecture derived from the 770M-parameter CodeT5 model with its decoder removed and a modified classification head. It achieves 95.8% accuracy on five-class attribution, 94.6% on ten-class, and 88.5% on twenty-class tasks, surpassing other tested models such as BERT, CodeBERT, and Longformer. We demonstrate that classifiers capture deeper stylistic regularities in program dataflow and structure, rather than relying on surface-level features. As a result, attribution remains effective even after mangling, comment removal, and heavy code transformations. To support open science and reproducibility, we release the LLM-NodeJS dataset, Google Colab training scripts, and all related materials on GitHub: https://github.com/LLM-NodeJS-dataset.

Norbert Tihanyi, Ridhi Jain, Yiannis Charalambous et al.

This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify vulnerabilities and extract counterexamples. These counterexamples are supported by mathematical proofs and the stack trace of the vulnerabilities. Using a specially designed prompt, we combine the original source code with the identified vulnerability, including its stack trace and counterexample that specifies the line number and error type. This combined information is then fed into an LLM, which is instructed to attempt to fix the code. The new code is subsequently verified again using BMC to ensure the fix succeeded. We present the ESBMC-AI framework as a proof of concept, leveraging the well-recognized and industry-adopted Efficient SMT-based Context-Bounded Model Checker (ESBMC) and a pre-trained transformer model to detect and fix errors in C programs, particularly in critical software components. We evaluated our approach on 50,000 C programs randomly selected from the FormAI dataset with their respective vulnerability classifications. Our results demonstrate ESBMC-AI's capability to automate the detection and repair of issues such as buffer overflow, arithmetic overflow, and pointer dereference failures with high accuracy. ESBMC-AI is a pioneering initiative, integrating LLMs with BMC techniques, offering potential integration into the continuous integration and deployment (CI/CD) process within the software development lifecycle.