Plataforma Inteligente para Ensino de Cibersegurança com Geração de Conteúdo Dinâmico

• Matheus B. Honório UFPB
• Herick José UFPB
• Clarissa Santos UFPB
• Danielle Rousy Dias Ricarte UFPB
• Raoni Kulesza UFPB

DOI: https://doi.org/10.5753/webmedia.2026.30823

Resumo

Cybersecurity education requires dynamic and continuously updated learning materials, given the rapid obsolescence of traditional resources. This work presents a Retrieval-Augmented Generation (RAG) architecture integrated into the educational platform to enable the dynamic generation of cybersecurity content. The solution combines semantic retrieval, prompt engineering, and automated evaluation through an LLM-as-a-Judge pipeline to produce multimodal content—including explanations, quizzes, flashcards and slides—derived from a specialized knowledge base of more than 2,100 pages. The approach was assessed across realistic instructional scenarios, with attention to groundedness, retrieval precision, pedagogical quality, and response adequacy. Results show 92% precision, 82% groundedness, and an 88.89% approval rate according to the evaluation rubric, indicating that the system generates accurate, contextualized, and educationally aligned content. The proposed architecture reduces material obsolescence, enhances personalization, and demonstrates the potential of RAG systems to support learning in complex domains such as cybersecurity.

Palavras-chave: Cybersecurity Education, Dynamic Content Generation, Gamification, Intelligent Tutoring Systems, Large Language Models, Retrieval-Augmented Generation

Referências

Rafael Dias Araújo. 2013. Distribuição e personalização de conteúdo multimídia em ambientes educacionais ubíquos. Dissertação de Mestrado. Universidade Federal de Uberlândia, Uberlândia. DOI: 10.14393/ufu.di.2013.309

João Campos, Marcelo Machado, Guilherme Lima, and Viviane Silva. 2025. Uma Ferramenta Web Baseada em LLMs para Respostas a Perguntas Simples sobre Bases de Conhecimento Heterogêneas. In Anais Estendidos do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (Rio de Janeiro/RJ). SBC, Porto Alegre, RS, Brasil, 159–162. DOI: 10.5753/webmedia_estendido.2025.16367

Mario Cannataro and Andrea Pugliese. 2000. An XML-based architecture for adaptive Web hypermedia systems using a probabilistic user model. In Proceedings of the 1st International Conference on Web Information Systems Engineering. IEEE, 1–8. DOI: 10.1109/WISE.2000.882386

Matheus Figueiredo e Silva, Levi Pereira Júnior, David Pereira, Beatriz Meneses, Kemilli Lima, José Araujo Junior, Leandro Marinho, and Eliane Araújo. 2025. EurecaChat: A Multi-Agent LLM-Based Chatbot for Supporting Students, Faculty, and University Administration. In Anais Estendidos do XXXI Simpósio Brasileiro de Sistemas Multimídia e Web (Rio de Janeiro/RJ). SBC, Porto Alegre, RS, Brasil, 107–110. DOI: 10.5753/webmedia_estendido.2025.16419

Shahul Es, Jithin James, Luis Espinosa-Anke, and Steven Schockaert. 2023. Ragas: Automated Evaluation of Retrieval Augmented Generation. arXiv:2309.15217 [cs.CL] [link]

Isabela Gasparini, José Palazzo Moreira de Oliveira, Marcelo S. Pimenta, José Valdeni de Lima, Avanilde Kemczinski, Mario L. Proença Jr, and Maria Angélica de O. Camargo Brunetto. 2010. AdaptWeb® - Evolução e Desafios. Cadernos de Informática 4, 2 (July 2010), 47–56. [link]

IBGE, Coordenação de Pesquisas por Amostra de Domicílios. 2025. Acesso à internet e à televisão e posse de telefone móvel celular para uso pessoal 2024. Technical Report. Instituto Brasileiro de Geografia e Estatística, Rio de Janeiro. [link]

Malcolm S. Knowles, Elwood F. Holton III, Richard A. Swanson, and Petra A. Robinson. 2020. The Adult Learner: The Definitive Classic in Adult Education and Human Resource Development (9th ed.). Routledge, New York, NY.

LangChain Contributors. 2024. MultiQueryRetriever. [link].

James C. Lester, Sharolyn A. Converse, Susan E. Kahler, S. Todd Barlow, Brian A. Stone, and Ravinder S. Bhogal. 1997. The persona effect: affective impact of animated pedagogical agents. In Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (Atlanta, Georgia, USA) (CHI ’97). Association for Computing Machinery, New York, NY, USA, 359–366. DOI: 10.1145/258549.258797

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledgeintensive NLP tasks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS ’20). Curran Associates Inc., Red Hook, NY, USA, Article 793, 16 pages.

Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, and Huan Liu. 2024. From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge. arXiv:2411.16594 [cs.AI] [link]

MITRE Corporation. 2023. MITRE ATT&CK: Phishing (T1566). [link].

MITRE Corporation. 2025. Common Vulnerabilities and Exposures (CVE®). [link]. Acesso em: 26 jun. 2026.

MITRE Corporation. 2025. MITRE ATT&CK®. [link]. Acesso em: 26 jun. 2026.

Madhav Mukherjee, John Le, and Yang-Wai Chow. 2025. Generative AI-Enhanced Intelligent Tutoring System for Graduate Cybersecurity Programs. Future Internet 17, 4 (2025), 154. DOI: 10.3390/fi17040154

National Institute of Standards and Technology. 2020. Data Integrity: Detecting and Responding to Ransomware and Other Destructive Events. Technical Report NIST SP 1800-26. National Institute of Standards and Technology. DOI: 10.6028/NIST.SP.1800-26

Francisco Ricarte Neto, Rafael Anchiêta, Raimundo Moura, Pedro Santos Neto, and Andre Santana. 2025. Investigating Contextual Word Embeddings in Semi-Supervised Learning for Toxic Comment Detection. In Proceedings of the 31st Brazilian Symposium on Multimedia and the Web (Rio de Janeiro/RJ). SBC, Porto Alegre, RS, Brasil, 330–339. DOI: 10.5753/webmedia.2025.15994

OpenAI. 2024. GPT-4o mini: Advancing Cost-Efficient Intelligence. [link]. Large language model. Accessed: 2026-06-25.

PromptFoo Contributors. 2024. PromptFoo: Test your prompts, agents, and RAGs. [link].

Gaurangi Raul, Yu-Zheng Lin, Karan Patel, Bono Po-Jen Shih, Matthew W. Redondo, Banafsheh Saber Latibari, Jesus Pacheco, Soheil Salehi, and Pratik Satam. 2025. RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented Tutoring. In 2025 IEEE Frontiers in Education Conference (FIE). 1–9. DOI: 10.1109/FIE63693.2025.11328742

Paula Toledo Palomino, Lennart Nacke, and Seiji Isotani. 2023. Gamificação Narrativa para Engajamento e Personalização: Redefinindo a Experiência do Aprendizado Digital. Anais Estendidos do Simpósio Brasileiro de Sistemas Multimídia e Web (WebMedia). DOI: 10.5753/webmedia_estendido.2023.233396

Mohammad Amaz Uddin and Iqbal H. Sarker. 2026. Fine-Tuning vs. RAG: A Position Paper from the Perspective of LLM-Based Cybersecurity Modeling. Computing&AI Connect 3 (2026), Article ID: 2026.0031. DOI: 10.69709/CAIC.2026.155073

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. [link]

Chengshuai Zhao, Garima Agrawal, Fan Zhang, Tharindu Kumarage, Zhen Tan, Yuli Deng, Ying-Chih Chen, and Huan Liu. 2025. Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education. arXiv:2412.14191 [cs.CY] [link]

Chengshuai Zhao, Riccardo De Maria, Tharindu Kumarage, Kumar Satvik Chaudhary, Garima Agrawal, Yiwen Li, Jongchan Park, Ying-Chih Chen, Yuli Deng, and Huan Liu. 2025. Cyber-BOT: Ontology-Grounded Retrieval Augmented Generation for Reliable Cybersecurity Education. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM ’25). ACM, 6752–6756. DOI: 10.1145/3746252.3761478

Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-bench and Chatbot Arena. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS ’23). Curran Associates Inc., Red Hook, NY, USA, Article 2020, 29 pages.

Ítalo Pereira and Anderson Ferreira. 2024. E-BELA: Enhanced Embedding-Based Entity Linking Approach. In Proceedings of the 30th Brazilian Symposium on Multimedia and the Web (Juiz de Fora/MG). SBC, Porto Alegre, RS, Brasil, 115–123. DOI: 10.5753/webmedia.2024.243160