LLM-Based Dishonesty and Excessive Collaboration Detection in Cybersecurity Education

Hofnăr, Aurel-Dragoş

doi:10.2478/sbeef-2025-0010

Abstract

Artificial intelligence long-term memory models are able to provide answers to a wide range of questions from a wide range of domains and to some extent, is able to detect excessive collaboration in the cybersecurity education field, making use of metadata (logs). There are some key differences between the models and the human factor with regards to completeness and correctness of the results. The aim of this paper is to provide an overview of the current state of the art of artificial intelligence and its use in detecting excessive collaboration in the cybersecurity education field.

References

D. Cotton, P. Cotton, and R. Shipway, “Chatting and Cheating: Ensuring academic integrity in the era of ChatGPT,” 2023.
Search in Google Scholar Back to article
A. Cotton, K. Patel, and S. Jennings, “Academic Integrity in the Age of Artificial Intelligence: Student and Faculty Perspectives on ChatGPT and Beyond,” Journal of Educational Technology, vol. 47, no. 2, pp. 155–170, 2023.
Search in Google Scholar Back to article
D. Owunwanne, N. Rustagi, and R. Dada, “Students Perceptions Of Cheating And Plagiarism In Higher Institutions,” Journal Of College Teaching & Learning (TLC), vol. 7, Nov. 2010.
Search in Google Scholar Back to article
T. Zhang, Y. Lu, et al., “A Survey on Large Language Models for AIAssisted Education,” arXiv preprint arXiv:2401.01641, 2024.
Search in Google Scholar Back to article
R. Beverly, et al., “Cybersecurity Education in the Age of AI: Opportunities and Challenges,” in Proc. USENIX Security Education Workshop (USEC), 2023.
Search in Google Scholar Back to article
J. Zou, O. Levy, et al., “Detecting AI-Generated Text: Current Approaches and Challenges,” Nature Machine Intelligence, vol. 5, pp. 500–510, 2023.
Search in Google Scholar Back to article
J. Wan, Y. Wang, and D. Wang, “Log-Based Detection of Collaborative Cheating in Online Exams,” IEEE Transactions on Learning Technologies, vol. 16, no. 1, pp. 12–21, 2023.
Search in Google Scholar Back to article
B. Erdem and M. Karabatak, “Cheating Detection in Online Exams Using Deep Learning and Machine Learning,” Applied Sciences, vol. 15, no. 1, art. 400, 2025. Available: https://www.mdpi.com/2076-3417/15/1/400, doi:10.3390/app15010400
Search in Google Scholar Back to article
X. Liu, Y. Zhang, J. Li, and Y. Chen, “Challenges and Perspectives on Detecting AI-Generated Content in Academic Settings,” Nature Human Behaviour, vol. 8, no. 3, pp. 315–320, 2024. doi:10.1038/s41562-024-01829-9.
Search in Google Scholar Back to article
OWASP ModSecurity Project. “ModSecurity Project,” [Online]. Available: https://modsecurity.org/ [Accessed: 27-Apr-2025].
Search in Google Scholar Back to article
OWASP ModSecurity Project. “ModSecurity 2 Data Formats,” [Online]. Available: https://github.com/owaspmodsecurity/ModSecurity/wiki/ModSecurity-2-Data-Formats.
Search in Google Scholar Back to article
J. He, M. Rungta, D. Koleczek, A. Sekhon, F. Wang, and S. Hasan, “Does Prompt Formatting Have Any Impact on LLM Performance?,” 2024. [Online]. Available: https://arxiv.org/abs/2411.10541
Search in Google Scholar Back to article
Yifan Zhou, Jingjing Liu, Wei Wang, et al., “A Comparison of Open-Source and Proprietary Large Language Models for Machine Reading Comprehension,” Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024. To appear. Available at: https://arxiv.org/abs/2312.16444
Search in Google Scholar Back to article
Shizhe Qiao, Yuxuan Fan, Xingxuan Jiang, et al., “LiveBench: A Challenging, Contamination-Free LLM Benchmark,” arXiv preprint arXiv:2405.18990, 2024. Available at: https://arxiv.org/abs/2405.18990
Search in Google Scholar Back to article
Jonathan Chavez Tamales and the LLM-Stats community, “LLM Stats: A Community-Driven Leaderboard for Large Language Models,” 2025. Available at: https://llm-stats.com/. Accessed: 2025-06-13.
Search in Google Scholar Back to article
Lea Nonninger, Microsoft-backed AI lab Mistral debuts reasoning model to rival OpenAI, 2025. https://www.cnbc.com/2025/06/10/microsoft-backed-ai-lab-mistral-debuts-reasoning-model-to-rival-openai.html. Accessed: 2025-06-13.
Search in Google Scholar Back to article

LLM-Based Dishonesty and Excessive Collaboration Detection in Cybersecurity Education

Abstract

Paradigm

My account