Skip to main content
PLOMSE AI
Open Access Cybersecurity Peer-reviewed

Exploring AI Bias in Security-Related Decision- Making

,

  1. Department of Information Systems, College of Economics, Management, and Information Systems, University of Nizwa, Nizwa, Sultanate of Oman.
  2. AI Applications Chair, University of Nizwa, Nizwa 616, Sultanate of Oman.

PLOMSE AI 2025, 5(1)

Submission received
27 September 2025
Accepted
15 July 2025
Published
15 July 2025
Download PDF Print

Abstract

The increasing penetration of large language models (LLMs) into so-called security domains raises many questions about whether potential biases exist that would affect sensitive decisions related to safety or security. These questions must be answered with a systematic investigation into possible biases on the part of these models towards different security scenarios. The study attempts to assess bias in the responses of the Grok language model with respect to security scenarios, paying particular attention to how the model assesses different demographic classes (race, gender, age, appearance) for threat potential. This study followed a multi-dimensional analytical process by submitting 15 security-related questions to the Grok model, whose responses were then analyzed both quantitatively and qualitatively. These analyses measured threat classification rates among different demographic groups; studied semantic connotations, inference schemes, and judged the model on the basis of consistency with self-claimed principles of fairness. Threat classification rates showed statistically significant differences among various demographic sectors. Arab/Middle Eastern, Black, young, and male individuals were rated as potential threats at much higher rates (51.4%, 43.7%, 48.3%, and 47.6%, respectively) compared to White, elderly, and female persons (36.2%, 27.5%, and 31.9%, respectively). The qualitative analysis also presented persistent contradictions between stated principles and actual practices, including selective use of statistics and arguably varying interpretive frameworks with respect to different demographic groups. The aspect of intersectional bias is particularly troubling, where "young Arab male in traditional clothing" was classified as a potential threat at a rate of 62.7%.

Keywords

AI biaslarge language modelsracial discriminationpredictive justiceintersectional biasalgorithmic critical analysis

© 2025 by the authors. Licensee PLOMSE, Richardson, TX, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 (CC BY 4.0) license.