Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gravereaux, Stephen C., Islam, Sheikh Rabiul
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.19654
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914169919373312
author Gravereaux, Stephen C.
Islam, Sheikh Rabiul
author_facet Gravereaux, Stephen C.
Islam, Sheikh Rabiul
contents This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware classification. Achieving trustworthy malware detection, particularly when LLMs are involved, remains a significant challenge. We developed an evaluation framework using Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), and Semantic Similarity Metrics to benchmark explanation quality across five LoRA configurations and a fully fine-tuned baseline. Results indicate that full fine-tuning achieves the highest overall scores, with BLEU and ROUGE improvements of up to 10% over LoRA variants. However, mid-range LoRA models deliver competitive performance exceeding full fine-tuning on two metrics while reducing model size by approximately 81% and training time by over 80% on a LoRA model with 15.5% trainable parameters. These findings demonstrate that LoRA offers a practical balance of interpretability and resource efficiency, enabling deployment in resource-constrained environments without sacrificing explanation quality. By providing feature-driven natural language explanations for malware classifications, this approach enhances transparency, analyst confidence, and operational scalability in malware detection systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning vs. Full Fine-Tuning
Gravereaux, Stephen C.
Islam, Sheikh Rabiul
Cryptography and Security
Artificial Intelligence
This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware classification. Achieving trustworthy malware detection, particularly when LLMs are involved, remains a significant challenge. We developed an evaluation framework using Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), and Semantic Similarity Metrics to benchmark explanation quality across five LoRA configurations and a fully fine-tuned baseline. Results indicate that full fine-tuning achieves the highest overall scores, with BLEU and ROUGE improvements of up to 10% over LoRA variants. However, mid-range LoRA models deliver competitive performance exceeding full fine-tuning on two metrics while reducing model size by approximately 81% and training time by over 80% on a LoRA model with 15.5% trainable parameters. These findings demonstrate that LoRA offers a practical balance of interpretability and resource efficiency, enabling deployment in resource-constrained environments without sacrificing explanation quality. By providing feature-driven natural language explanations for malware classifications, this approach enhances transparency, analyst confidence, and operational scalability in malware detection systems.
title Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning vs. Full Fine-Tuning
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2511.19654