AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gungor, Onat, Sood, Roshan, Wang, Harold, Rosing, Tajana
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915497807708160
author Gungor, Onat
Sood, Roshan
Wang, Harold
Rosing, Tajana
author_facet Gungor, Onat
Sood, Roshan
Wang, Harold
Rosing, Tajana
contents Large Language Models (LLMs) have recently demonstrated strong potential for cybersecurity question answering (QA), supporting decision-making in real-time threat detection and response workflows. However, their substantial computational demands pose significant challenges for deployment on resource-constrained edge devices. Quantization, a widely adopted model compression technique, can alleviate these constraints. Nevertheless, quantization may degrade model accuracy and increase susceptibility to adversarial attacks. Fine-tuning offers a potential means to mitigate these limitations, but its effectiveness when combined with quantization remains insufficiently explored. Hence, it is essential to understand the trade-offs among accuracy, efficiency, and robustness. We propose AQUA-LLM, an evaluation framework designed to benchmark several state-of-the-art small LLMs under four distinct configurations: base, quantized-only, fine-tuned, and fine-tuned combined with quantization, specifically for cybersecurity QA. Our results demonstrate that quantization alone yields the lowest accuracy and robustness despite improving efficiency. In contrast, combining quantization with fine-tuning enhances both LLM robustness and predictive performance, achieving an optimal balance of accuracy, robustness, and efficiency. These findings highlight the critical need for quantization-aware, robustness-preserving fine-tuning methodologies to enable the robust and efficient deployment of LLMs for cybersecurity QA.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13514
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering
Gungor, Onat
Sood, Roshan
Wang, Harold
Rosing, Tajana
Cryptography and Security
Large Language Models (LLMs) have recently demonstrated strong potential for cybersecurity question answering (QA), supporting decision-making in real-time threat detection and response workflows. However, their substantial computational demands pose significant challenges for deployment on resource-constrained edge devices. Quantization, a widely adopted model compression technique, can alleviate these constraints. Nevertheless, quantization may degrade model accuracy and increase susceptibility to adversarial attacks. Fine-tuning offers a potential means to mitigate these limitations, but its effectiveness when combined with quantization remains insufficiently explored. Hence, it is essential to understand the trade-offs among accuracy, efficiency, and robustness. We propose AQUA-LLM, an evaluation framework designed to benchmark several state-of-the-art small LLMs under four distinct configurations: base, quantized-only, fine-tuned, and fine-tuned combined with quantization, specifically for cybersecurity QA. Our results demonstrate that quantization alone yields the lowest accuracy and robustness despite improving efficiency. In contrast, combining quantization with fine-tuning enhances both LLM robustness and predictive performance, achieving an optimal balance of accuracy, robustness, and efficiency. These findings highlight the critical need for quantization-aware, robustness-preserving fine-tuning methodologies to enable the robust and efficient deployment of LLMs for cybersecurity QA.
title AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering
topic Cryptography and Security
url https://arxiv.org/abs/2509.13514