Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls

• URL: http://arxiv.org/abs/2405.09318v1
• Date: Wed, 15 May 2024 13:19:43 GMT
• Title: Transfer Learning in Pre-Trained Large Language Models for Malware Detection Based on System Calls
• Authors: Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Gérôme Bovet, Gregorio Martínez Pérez,
• Abstract summary: This work presents a novel framework leveraging large language models (LLMs) to classify malware based on system call data. Experiments with a dataset of over 1TB of system calls demonstrate that models with larger context sizes, such as BigBird and Longformer, achieve superior accuracy and F1-Score of approximately 0.86. This approach shows significant potential for real-time detection in high-stakes environments, offering a robust solution to evolving cyber threats.
• Score: 3.5698678013121334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the current cybersecurity landscape, protecting military devices such as communication and battlefield management systems against sophisticated cyber attacks is crucial. Malware exploits vulnerabilities through stealth methods, often evading traditional detection mechanisms such as software signatures. The application of ML/DL in vulnerability detection has been extensively explored in the literature. However, current ML/DL vulnerability detection methods struggle with understanding the context and intent behind complex attacks. Integrating large language models (LLMs) with system call analysis offers a promising approach to enhance malware detection. This work presents a novel framework leveraging LLMs to classify malware based on system call data. The framework uses transfer learning to adapt pre-trained LLMs for malware detection. By retraining LLMs on a dataset of benign and malicious system calls, the models are refined to detect signs of malware activity. Experiments with a dataset of over 1TB of system calls demonstrate that models with larger context sizes, such as BigBird and Longformer, achieve superior accuracy and F1-Score of approximately 0.86. The results highlight the importance of context size in improving detection rates and underscore the trade-offs between computational complexity and performance. This approach shows significant potential for real-time detection in high-stakes environments, offering a robust solution to evolving cyber threats.

Related papers

• Attention Tracker: Detecting Prompt Injection Attacks in LLMs [62.247841717696765]
  Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks. We introduce the concept of the distraction effect, where specific attention heads shift focus from the original instruction to the injected instruction. We propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2024-11-01T04:05:59Z)
• Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability [44.99833362998488]
  Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. LLMs in particular are known to be vulnerable to adversarial attacks, where an imperceptible change to the input can mislead the output of the model. We propose a method, based on Mechanistic Interpretability (MI) techniques, to guide this process.
  arXiv  Detail & Related papers  (2024-07-29T09:55:34Z)
• M2CVD: Enhancing Vulnerability Semantic through Multi-Model Collaboration for Code Vulnerability Detection [52.4455893010468]
  Large Language Models (LLMs) have strong capabilities in code comprehension, but fine-tuning costs and semantic alignment issues limit their project-specific optimization. Code models such CodeBERT are easy to fine-tune, but it is often difficult to learn vulnerability semantics from complex code languages. This paper introduces the Multi-Model Collaborative Vulnerability Detection approach (M2CVD) to improve the detection accuracy of code models.
  arXiv  Detail & Related papers  (2024-06-10T00:05:49Z)
• Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models [8.167614500821223]
  We introduce MSIVD, multitask self-instructed fine-tuning for vulnerability detection, inspired by chain-of-thought prompting and LLM self-instruction. Our experiments demonstrate that MSIVD achieves superior performance, outperforming the highest LLM-based vulnerability detector baseline (LineVul) with a F1 score of 0.92 on the BigVul dataset, and 0.48 on the PreciseBugs dataset.
  arXiv  Detail & Related papers  (2024-06-09T19:18:05Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• A survey on hardware-based malware detection approaches [45.24207460381396]
  Hardware-based malware detection approaches leverage hardware performance counters and machine learning prowess. We meticulously analyze the approach, unraveling the most common methods, algorithms, tools, and datasets that shape its contours. The discussion extends to crafting mixed hardware and software approaches for collaborative efficacy, essential enhancements in hardware monitoring units, and a better understanding of the correlation between hardware events and malware applications.
  arXiv  Detail & Related papers  (2023-03-22T13:00:41Z)
• Harnessing the Speed and Accuracy of Machine Learning to Advance Cybersecurity [0.0]
  Traditional signature-based methods of malware detection have limitations in detecting complex threats. In recent years, machine learning has emerged as a promising solution to detect malware effectively. ML algorithms are capable of analyzing large datasets and identifying patterns that are difficult for humans to identify.
  arXiv  Detail & Related papers  (2023-02-24T02:42:38Z)
• Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems [0.0]
  This paper evaluates the robustness of six recent deep learning algorithms for intrusion detection on contaminated data. Our experiments suggest that the state-of-the-art algorithms used in this study are sensitive to data contamination and reveal the importance of self-defense against data perturbation.
  arXiv  Detail & Related papers  (2022-06-25T02:28:39Z)
• Adversarial Machine Learning Threat Analysis in Open Radio Access Networks [37.23982660941893]
  The Open Radio Access Network (O-RAN) is a new, open, adaptive, and intelligent RAN architecture. In this paper, we present a systematic adversarial machine learning threat analysis for the O-RAN.
  arXiv  Detail & Related papers  (2022-01-16T17:01:38Z)
• ML-based IoT Malware Detection Under Adversarial Settings: A Systematic Evaluation [9.143713488498513]
  This work systematically examines the state-of-the-art malware detection approaches, that utilize various representation and learning techniques. We show that software mutations with functionality-preserving operations, such as stripping and padding, significantly deteriorate the accuracy of such detectors.
  arXiv  Detail & Related papers  (2021-08-30T16:54:07Z)
• Interpreting Machine Learning Malware Detectors Which Leverage N-gram Analysis [2.6397379133308214]
  cybersecurity analysts always prefer solutions that are as interpretable and understandable as rule-based or signature-based detection. The objective of this paper is to evaluate the current state-of-the-art ML models interpretability techniques when applied to ML-based malware detectors.
  arXiv  Detail & Related papers  (2020-01-27T19:10:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.