arXiv subjects

Mohamed Amine Ferrag

Publications and source records attributed to Mohamed Amine Ferrag.

At least 37 records · Page 2Linked to original sources

arXiv2025

CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection

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.

cs.CR↗

arXiv2025

Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview

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.

cs.SE↗

arXiv2025

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?

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.

cs.CR↗

arXiv2025

Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities

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.

cs.CR↗

arXiv2024

GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models

Cyber timeline analysis, or forensic timeline analysis, is crucial in Digital Forensics and Incident Response (DFIR). It examines artefacts and events particularly timestamps and metadata to detect anomalies, establish correlations, and reconstruct incident timelines. Traditional methods rely on structured artefacts, such as logs and filesystem metadata, using specialised tools for evidence identification and feature extraction. This paper introduces GenDFIR, a framework leveraging large language models (LLMs), specifically Llama 3.1 8B in zero shot mode, integrated with a Retrieval-Augmented Generation (RAG) agent. Incident data is preprocessed into a structured knowledge base, enabling the RAG agent to retrieve relevant events based on user prompts. The LLM interprets this context, offering semantic enrichment. Tested on synthetic data in a controlled environment, results demonstrate GenDFIR's reliability and robustness, showcasing LLMs potential to automate timeline analysis and advance threat detection.

cs.CR↗

arXiv2024

How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models

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.

cs.CR↗

arXiv2024

Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence

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.

cs.AI↗

arXiv2024

Securing Tomorrow's Smart Cities: Investigating Software Security in Internet of Vehicles and Deep Learning Technologies

Integrating Deep Learning (DL) techniques in the Internet of Vehicles (IoV) introduces many security challenges and issues that require thorough examination. This literature review delves into the inherent vulnerabilities and risks associated with DL in IoV systems, shedding light on the multifaceted nature of security threats. Through an extensive analysis of existing research, we explore potential threats posed by DL algorithms, including adversarial attacks, data privacy breaches, and model poisoning. Additionally, we investigate the impact of DL on critical aspects of IoV security, such as intrusion detection, anomaly detection, and secure communication protocols. Our review emphasizes the complexities of ensuring the robustness, reliability, and trustworthiness of DL-based IoV systems, given the dynamic and interconnected nature of vehicular networks. Furthermore, we discuss the need for novel security solutions tailored to address these challenges effectively and enhance the security posture of DL-enabled IoV environments. By offering insights into these critical issues, this chapter aims to stimulate further research, innovation, and collaboration in securing DL techniques within the context of the IoV, thereby fostering a safer and more resilient future for vehicular communication and connectivity.

cs.CR↗

arXiv2024

A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification

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.

cs.SE↗

arXiv2024

CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge

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.

cs.AI↗

arXiv2024

Critical Infrastructure Protection: Generative AI, Challenges, and Opportunities

Critical National Infrastructure (CNI) encompasses a nation's essential assets that are fundamental to the operation of society and the economy, ensuring the provision of vital utilities such as energy, water, transportation, and communication. Nevertheless, growing cybersecurity threats targeting these infrastructures can potentially interfere with operations and seriously risk national security and public safety. In this paper, we examine the intricate issues raised by cybersecurity risks to vital infrastructure, highlighting these systems' vulnerability to different types of cyberattacks. We analyse the significance of trust, privacy, and resilience for Critical Infrastructure Protection (CIP), examining the diverse standards and regulations to manage these domains. We also scrutinise the co-analysis of safety and security, offering innovative approaches for their integration and emphasising the interdependence between these fields. Furthermore, we introduce a comprehensive method for CIP leveraging Generative AI and Large Language Models (LLMs), giving a tailored lifecycle and discussing specific applications across different critical infrastructure sectors. Lastly, we discuss potential future directions that promise to enhance the security and resilience of critical infrastructures. This paper proposes innovative strategies for CIP from evolving attacks and enhances comprehension of cybersecurity concerns related to critical infrastructure.

cs.CR↗

arXiv2024

The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification

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.

cs.DB↗

arXiv2024

Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses

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) applications. These 5G challenges are behind worldwide efforts to enable future networks, such as sixth generation (6G) networks, to efficiently support sophisticated applications ranging from autonomous driving capabilities to the Metaverse. Edge learning is a new and powerful approach to training models across distributed clients while protecting the privacy of their data. This approach is expected to be embedded within future network infrastructures, including 6G, to solve challenging problems such as resource management and behavior prediction. This survey article provides a holistic review of the most recent research focused on edge learning vulnerabilities and defenses for 6G-enabled IoT. We summarize the existing surveys on machine learning for 6G IoT security and machine learning-associated threats in three different learning modes: centralized, federated, and distributed. Then, we provide an overview of enabling emerging technologies for 6G IoT intelligence. Moreover, we provide a holistic survey of existing research on attacks against machine learning and classify threat models into eight categories, including backdoor attacks, adversarial examples, combined attacks, poisoning attacks, Sybil attacks, byzantine attacks, inference attacks, and dropping attacks. In addition, we provide a comprehensive and detailed taxonomy and a side-by-side comparison of the state-of-the-art defense methods against edge learning vulnerabilities. Finally, as new attacks and defense technologies are realized, new research and future overall prospects for 6G-enabled IoT are discussed.

cs.CR↗

arXiv2024

Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices

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.

cs.CR↗

arXiv2024

Adversarial Attacks and Defenses in 6G Network-Assisted IoT Systems

The Internet of Things (IoT) and massive IoT systems are key to sixth-generation (6G) networks due to dense connectivity, ultra-reliability, low latency, and high throughput. Artificial intelligence, including deep learning and machine learning, offers solutions for optimizing and deploying cutting-edge technologies for future radio communications. However, these techniques are vulnerable to adversarial attacks, leading to degraded performance and erroneous predictions, outcomes unacceptable for ubiquitous networks. This survey extensively addresses adversarial attacks and defense methods in 6G network-assisted IoT systems. The theoretical background and up-to-date research on adversarial attacks and defenses are discussed. Furthermore, we provide Monte Carlo simulations to validate the effectiveness of adversarial attacks compared to jamming attacks. Additionally, we examine the vulnerability of 6G IoT systems by demonstrating attack strategies applicable to key technologies, including reconfigurable intelligent surfaces, massive multiple-input multiple-output (MIMO)/cell-free massive MIMO, satellites, the metaverse, and semantic communications. Finally, we outline the challenges and future developments associated with adversarial attacks and defenses in 6G IoT systems.

cs.IT↗

arXiv2023

Distance-Only Task Orchestration Algorithm for Energy Efficiency in Satellite-Based Mist Computing

This paper addresses the challenge of efficiently offloading heavy computing tasks from ground mobile devices to the satellite-based mist computing environment. With ground-based edge and cloud servers often being inaccessible, the exploitation of satellite mist computing becomes imperative. Existing offloading algorithms have shown limitations in adapting to the unique characteristics of heavy computing tasks. Thus, we propose a heavy computing task offloading algorithm that prioritizes satellite proximity. This approach not only reduces energy consumption during telecommunications but also ensures tasks are executed within the specified timing constraints, which are typically non-time-critical. Our proposed algorithm outperforms other offloading schemes in terms of satellites energy consumption, average end-to-end delay, and tasks success rates. Although it exhibits a higher average VM CPU usage, this increase does not pose critical challenges. This distance-based approach offers a promising solution to enhance energy efficiency in satellite-based mist computing, making it well-suited for heavy computing tasks demands.

cs.CR↗

arXiv2023

Reliability Analysis of Fault Tolerant Memory Systems

This paper delves into a comprehensive analysis of fault-tolerant memory systems, focusing on recovery techniques modeled using Markov chains to address transient errors. The study revolves around the application of scrubbing methods in conjunction with Single Error Correction and Double Error Detection (SEC-DED) codes. It explores three primary models: 1) Exponentially distributed scrubbing, involving periodic checks of memory words within exponentially distributed time intervals; 2) Deterministic scrubbing, featuring regular, periodic word checks; and 3) Mixed scrubbing, which combines both probabilistic and deterministic scrubbing approaches. The research encompasses the estimation of reliability and Mean Time to Failure (MTTF) values for each model. Notably, the findings highlight the superior performance of mixed scrubbing over simpler scrubbing methods in terms of reliability and MTTF.

cs.DC↗

arXiv2023

Generative Adversarial Networks-Driven Cyber Threat Intelligence Detection Framework for Securing Internet of Things

While the benefits of 6G-enabled Internet of Things (IoT) are numerous, providing high-speed, low-latency communication that brings new opportunities for innovation and forms the foundation for continued growth in the IoT industry, it is also important to consider the security challenges and risks associated with the technology. In this paper, we propose a two-stage intrusion detection framework for securing IoTs, which is based on two detectors. In the first stage, we propose an adversarial training approach using generative adversarial networks (GAN) to help the first detector train on robust features by supplying it with adversarial examples as validation sets. Consequently, the classifier would perform very well against adversarial attacks. Then, we propose a deep learning (DL) model for the second detector to identify intrusions. We evaluated the proposed approach's efficiency in terms of detection accuracy and robustness against adversarial attacks. Experiment results with a new cyber security dataset demonstrate the effectiveness of the proposed methodology in detecting both intrusions and persistent adversarial examples with a weighted avg of 96%, 95%, 95%, and 95% for precision, recall, f1-score, and accuracy, respectively.

cs.CR↗