The paradigm of hallucinations in AI-driven cybersecurity systems: Understanding taxonomy, classification outcomes, and mitigations

Sood, Aditya K; Zeadally, Sherali; Hong, EenKee

doi:10.1016/j.compeleceng.2025.110307

Cited by 33Adversarial Robustness in Machine LearningInformation and Cyber SecurityNetwork Security and Intrusion Detection

The paradigm of hallucinations in AI-driven cybersecurity systems: Understanding taxonomy, classification outcomes, and mitigations

Sood, Aditya K, Zeadally, Sherali, Hong, EenKee·2025·Computers and Electrical Engineering

DOI 10.1016/j.compeleceng.2025.110307

Open this paper in CoChat — free account

Integrity signals

Registry

Crossref · 10.1016/j.compeleceng.2025.110307

Cites

25 of 25 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

A certain degree of hallucination is intrinsic to models that generalize from their training distributions.
“and the literature indicates that a certain degree of hallucination is intrinsic to models that generalize from their training distributions [17], [18], [19].”
From The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines (2026) · cites this paper as [17]

Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676 · see citing works
Proceedings of the 3rd International Conference on Neural Information Processing Systems
Lippmann, R. P., Moody, J. E., & Touretzky, D. S. (1990) · Cited by 1,204 · see citing works
A Survey of Deep Active Learning
Ren, P., Xiao, Y., Chang, X., Huang, P.-Y., Li, Z., Gupta, B. B., Chen, X., & Wang, X. (2022) · ACM Computing Surveys · doi:10.1145/3472291 · Cited by 1,169 · see citing works
To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making
Buçinca, Z., Malaya, M. B., & Gajos, K. Z. (2021) · arXiv · doi:10.48550/arxiv.2102.09692 · Cited by 1,124 · see citing works
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., & Li, Q. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671470 · Cited by 827 · see citing works
Defending Against Neural Fake News
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1905.12616 · Cited by 569 · see citing works
A Review of Trustworthy and Explainable Artificial Intelligence (XAI)
Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B. (2023) · IEEE Access · doi:10.1109/access.2023.3294569 · Cited by 352 · see citing works
Harnessing Artificial Intelligence Capabilities to Improve Cybersecurity
Zeadally, S., Adi, E., Baig, Z. A., & Khan, I. A. (2020) · IEEE Access · doi:10.1109/access.2020.2968045 · Cited by 334 · see citing works
Self-citation
From Machine Learning to Explainable AI
Holzinger, A. (2018) · 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA) · doi:10.1109/disa.2018.8490530 · Cited by 306 · see citing works
Automatic Chain of Thought Prompting in Large Language Models
Zhang, Z., Zhang, A., Li, M., & Smola, A. (2022) · arXiv · doi:10.48550/arxiv.2210.03493 · Cited by 274 · see citing works
A Meta-Analysis of Overfitting in Machine Learning
Roelofs, R., Shankar, V., Recht, B., Fridovich-Keil, S., Hardt, M., Miller, J. J., & Schmidt, L. (2019) · neural information processing systems · Cited by 138 · see citing works
Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
Chen, Y., Fu, Q., Yuan, Y., Wen, Z., Fan, G., Liu, D., Zhang, D., Li, Z., & Xiao, Y. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3614905 · Cited by 103 · see citing works
Word sense disambiguation: A complex network approach
Corrêa, E. A., Lopes, A. A., & Amancio, D. R. (2018) · Information Sciences · doi:10.1016/j.ins.2018.02.047 · Cited by 87 · see citing works
The effects of explanations on automation bias
Vered, M., Livni, T., Howe, P. D. L., Miller, T., & Sonenberg, L. (2023) · Artificial Intelligence · doi:10.1016/j.artint.2023.103952 · Cited by 71 · see citing works
How Smart Machines Think
Gerrish, S. (2018) · The MIT Press eBooks · doi:10.7551/mitpress/11440.001.0001 · Cited by 52 · see citing works
Machine Learning (In) Security: A Stream of Problems
Ceschin, F., Botacin, M. F., Bifet, A., Pfahringer, B., Oliveira, L. S., Gomes, H. M., & Gregio, A. R. A. (2023) · Digital Threats Research and Practice · doi:10.1145/3617897 · Cited by 51 · see citing works
GPTs and Hallucination
Waldo, J., & Boussard, S. (2024) · Queue · doi:10.1145/3688007 · Cited by 28 · see citing works
A Systematic Review on Semantic Role Labeling for Information Extraction in Low-Resource Data
Ariyanto, A. D. P., Purwitasari, D., & Fatichah, C. (2024) · IEEE Access · doi:10.1109/access.2024.3392370 · Cited by 20 · see citing works
The Ethics of Artificial Intelligence: exacerbated problems, renewed problems, unprecedented problems - Introduction to the Special Issue of the American Philosophical Quarterly dedicated to The Ethics of AIPreprint
Floridi, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4801799 · Cited by 19 · see citing works
Undecidability of Underfitting in Learning Algorithms
Sehra, S., Flores, D., & Montañez, G. D. (2021) · 2021 2nd International Conference on Computing and Data Science (CDS) · doi:10.1109/cds52072.2021.00107 · Cited by 19 · see citing works
Are Traditional Neural Networks Well-Calibrated?
Johansson, U., & Gabrielsson, P. (2019) · doi:10.1109/ijcnn.2019.8851962 · Cited by 10 · see citing works
Generative AI and Retrieval-Augmented Generation (RAG) Systems for Enterprise
Xu, A., Yu, T., Du, M., Gundecha, P., Guo, Y., Zhu, X., Wang, M., Li, P., & Chen, X. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3680117 · Cited by 10 · see citing works
Ethical Issues From Emerging AI Applications: Harms Are Happening
Grodzinsky, F. S., Wolf, M. J., & Miller, K. (2024) · Computer · doi:10.1109/mc.2023.3332850 · Cited by 8 · see citing works
On the Use of AutoML for Combating Alert Fatigue in Security Operations Centers
Preuveneers, D., Llamas, J. M., Bulut, İ., Rúa, E. A., Verfaillie, P., Demortier, V., Surinx, D., & Joosen, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-54129-2_36 · Cited by 4 · see citing works

Flagged first, then by citations

Sorted by citations

How does artificial intelligence adoption shape employee performance? A novel exploration of mimetic artificial intelligence performance through a hybrid approach based on PLS-SEM and ANN
Liu, S., & Mei, Y. (2025) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2025.124387 · Cited by 19 · see citing works
Towards a LLM-based intelligent system for detecting propaganda within textual content
Gaeta, A., Loia, V., Lorusso, A., Orciuoli, F., & Pascuzzo, A. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110765 · Cited by 11 · see citing works
A Lifecycle-Oriented Survey of Emerging Threats and Vulnerabilities in Large Language Models
de Maio, C., Di Gisi, M., Fenza, G., Gallo, M., & Loia, V. (2025) · IEEE Access · doi:10.1109/access.2025.3619764 · Cited by 10 · see citing works
LLM-Driven APT Detection for 6G Wireless Networks: A Systematic Review and Taxonomy
Golec, M., Khamayseh, Y., Melhem, S. B., & Alwarafy, A. (2025) · IEEE Access · doi:10.1109/access.2025.3595665 · Cited by 9 · see citing works
DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response
Cherif, B., Bisztray, T., Dubniczky, R. A., Aldahmani, A., Alshehhi, S., & Tihanyi, N. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4367-0_2 · Cited by 6 · see citing works
The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines
Vinay, V. (2026) · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395809 · Cited by 15 · see citing works
“…be important, particularly in security, and they have all been found to hallucinate (producing fluent but factually incorrect statements), and the literature indicates that a certain degree of hallucination is intrinsic to models that generalize from their training distributions [17], [18], [19].”
Penetration testing: Taxonomies, trade-offs, and adaptive strategies
Kapur, S., & Saurabh, P. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110686 · Cited by 3 · see citing works
Artificial Intelligence in the Energy Sector: Regulatory Compliance, Challenges, and Cybersecurity Implications
Fathy, R. A. (2025) · IEEE Conference on Power Electronics and Renewable Energy (CPERE) · doi:10.1109/cpere65146.2025.11240055 · Cited by 2 · see citing works
Accuracy, reliability, and regulatory concerns in the use of AI tools in education and research
AllahRakha, N. (2026) · Social Sciences & Humanities Open · doi:10.1016/j.ssaho.2026.103102 · Cited by 2 · see citing works
Hallucinations in generative artificial intelligence and large language models: tests, datasets, detection and correction methods
Naser, M. Z. (2026) · Language Resources and Evaluation · doi:10.1007/s10579-026-09938-4 · Cited by 2 · see citing works
AI Hallucination in Financial Systems
Harke, G. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7534-2.ch009 · Cited by 1 · see citing works
Toward sustainable and resilient omnichannel supply chains: prioritizing AI adoption risks through grey influence analysis and grey DEMATEL
Virmani, N., Gupta, S., & Singh, N. K. (2026) · Nankai Business Review International · doi:10.1108/nbri-12-2025-0170 · Cited by 1 · see citing works
EXPLORING THE BOUNDARIES OF ARTIFICIAL INTELLIGENCE HALLUCINATION
J, P. K. H. R. P. G. (2025) · International Journal of Apllied Mathematics · doi:10.12732/ijam.v38i2s.98
RFD-YOLO: Multi-Level Feature Fusion and Scale-Adaptive Framework for Steel Surface Defect Detection
Peng, Y., He, S. T., Shi, J., Liu, B., Liu, Y., & Tang, F. (2025) · International Conference on Advanced Computing and Intelligent Robotics Applications (ACIRA) · doi:10.1109/acira67680.2025.11334854
Advanced Malware Analysis and Detection Using Deep Neural Networks
Dominic Andrew, P., Jose, A. M., Jayapandian, N., Angel, C. S., & Brar, K. (2025) · IEEE International Conference on Data, Decision and Systems (ICDDS) · doi:10.1109/icdds67737.2025.11344689
A Comprehensive Evaluation of Large Language Models: Capabilities, Challenges, and Cross-Domain Applications
Vanmala, & Dubey, A. K. (2025) · International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) · doi:10.1109/icrcicn68210.2025.11364831
The Enterprise Metaverse
Alifen, A., Sekti, B. A., Pamungkas, V. A., Asri, J. S., Laksana, R. P., & Beth, B. D. C. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7534-2.ch007
AI Hallucinations in Retrieval-Augmented and Generative Systems: A Rigorous Review of Definitions, Failure Mechanisms, Evaluation, and Mitigation Strategies
Mzili, T., Mzili, I., Abatal, A., Oughannou, Z., Arya, A. K., & Kurdi, M. Z. (2026) · EDRAAK · doi:10.70470/edraak/2026/004
Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs Via a Structured Prompt Framework
Zhou, J., Adeseye, A., Virtanen, S., Hakkala, A., & Isoaho, J. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32732-1_9
A System-Level Taxonomy of Failure Modes in Large Language Model Applications
Vinay, V. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536235
Enhancing the quality and trustworthiness of large language model-generated summaries of clinical oncology literature
Stenzl, A., Rogers, E., Ananiadou, S., Wang, Y., Armstrong, A. J., Sboner, A., Cacciamani, G. E., Schijvenaars, B. J. A., Ahmed, K. R., Thomsen, H., et al. (2026) · JAMIA Open · doi:10.1093/jamiaopen/ooag078
SafeAIMerge: A Tool for Integrating DAST and LLM-Generated Security Feedback into GitHub Actions Workflows
Thool, A., Smith, J., & Brown, C. (2026) · IEEE Secure Development Conference (SecDev) · doi:10.1145/3805773.3806003
Towards Verified Security: Formal Methods for LLM-Based Defenses
Daukševič, D., Carrión, R. M., & Laibinis, L. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587351
A flawed compass in the info-fog: Effect of AI hallucinations on tourists’ sequential decision-making
Wang, J., Tang, Y., Chen, X., Peng, H., & Zhang, Y. (2026) · Journal of Hospitality and Tourism Management · doi:10.1016/j.jhtm.2026.101531
Analysis of Cybersecurity Intelligence Attacks in Nigeria: An AI-Assisted Platform for Detection, Mitigation and Combating Digital Threats Using DeepSeek Integration
Orji Cyrus Ebere, M. C. P. N., Nosike, P., Ononiwu Chamberlyn, C., & 3Ukachukwu, T. N. (2026) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt/26jul1684
Large Language Model-Assisted Threat-Driven Testing System for Enhanced Cybersecurity Readiness
Nze, P. E., Ademuwagun, A. K., Bello, M., Ifeanyi, F. D., Abdullahi, S. M., & Tighil, J. (2026) · Journal of Cyber Security · doi:10.32604/jcs.2026.083943
DA ALUCINAÇÃO DA IA AO CONHECIMENTO VALIDADO: O PAPEL DA COLABORAÇÃO HUMANA
Pinto, F. M. D. C., Marques, J. N., SILVA, R. M. D., & Moreira, J. A. (2026) · Revista Tópicos. · doi:10.70773/revistatopicos/790001371
Development of a theoretical model for calibrating trust in AI to augment highways safety
Ivvala, P., Bayramova, A., Roberts, C. J., Edwards, D. J., & Rillie, I. (2026) · Smart and Sustainable Built Environment · doi:10.1108/sasbe-05-2026-0485
Artificial Intelligence-Driven Cybersecurity in Resource-Constrained Environments: Challenges and Future Directions
Mirholikov, M., Allanov, O., Musaev, M., Abdirayimov, R., Murodjonov, L., Kyamakya, K., & Kasereka, S. K. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.08.468
ARTIFICIAL INTELLIGENCE AS A DRIVER OF PREDICTIVE ORGANIZATIONAL RESILIENCE: A SYNTHESIS OF CURRENT RESEARCH AND FUTURE DECISIONS
(2026) · Issues in Information Systems · doi:10.48009/2_iis_2026_138
Enabling Multi-Agent Penetration Testing Environments for Software Vulnerability Detection
Madisetti, R. K., Chawla, S., & Madisetti, V. K. (2026) · Journal of Information Security · doi:10.4236/jis.2026.174023
Corporate cybersecurity governance and open innovation: evidence from China
Zhang, X., Chen, J., & Dong, L. (2026) · Applied Economics · doi:10.1080/00036846.2026.2754317
EdgeGuard: Source-aware robustness and edge-feasibility evaluation of lightweight email phishing detectors under cross-LLM generated attacks
Bibi, M., Awan, K. A., Liu, L.-C., Chen, C.-L., Alanazi, F., Alanazi, M. H., & Uddin, M. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01351-9

Authors: Sood, A. K., Zeadally, S., & Hong, E.
Affiliations: University of Kentucky (US)
Corresponding author: Zeadally, Sherali
ORCID: Sood, Aditya K
Zeadally, Sherali
Venue: Computers and Electrical Engineering
Publisher: Elsevier BV
Published: 2025-05
Volume: 124
Pages: 110307
ISSN: 0045-7906 (ISSN-L)
DOI: 10.1016/j.compeleceng.2025.110307
OpenAlex: W4409198830
Cited by: 33
References: 24
Citations by year: 2026: 22 · 2025: 11
FWCI: 10.76
Type: journal article
Language: en
Open access: closed
Licence: www.elsevier.com/tdm/userlicense/1.0/ (tdm)
www.elsevier.com/legal/tdmrep-license (tdm)
doi.org/10.15223/policy-017 (stm-asf)
doi.org/10.15223/policy-037 (stm-asf)
doi.org/10.15223/policy-012 (stm-asf)
doi.org/10.15223/policy-029 (stm-asf)
doi.org/10.15223/policy-004 (stm-asf)
Locations: Computers & Electrical Engineering (publishedVersion)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
Keywords: hallucinations, large language models, artificial intelligence in cybersecurity, hallucination taxonomy, threat detection, hallucination mitigation, human oversight, trust in automation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

The paradigm of hallucinations in AI-driven cybersecurity systems: Understanding taxonomy, classification outcomes, and mitigations

Integrity signals

Claims the paper makes

Claims other papers make about this one

Cites

Cited by

Related

Record

About these checks