Metraipolis › archive › dc_a141b294372d
Evaluating the Impact of Personalization in Conversational Cybersecurity Assistants — arXiv:2609.17839
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17839
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:31:33.498Z
- SHA-256 of the archived text
e959fb7cd4bfd57765387659b332041f1ff901a511106d92e9eae88ed5959d3e- Stable URL of this page
https://metraipolis.com/documento/dc_a141b294372d
How to cite
Evaluating the Impact of Personalization in Conversational Cybersecurity Assistants — arXiv:2609.17839 — arXiv (en), https://arxiv.org/abs/2609.17839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a141b294372d (Metraipolis archive dc_a141b294372d, sha256 e959fb7cd4bfd57765387659b332041f1ff901a511106d92e9eae88ed5959d3e)
BibTeX
@misc{dca141b294372d,
title = {Evaluating the Impact of Personalization in Conversational Cybersecurity Assistants — arXiv:2609.17839},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17839},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a141b294372d; sha256 e959fb7cd4bfd57765387659b332041f1ff901a511106d92e9eae88ed5959d3e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Users increasingly turn to Large Language Models to answer a variety of questions, including cybersecurity questions. We study how personalization strategies can help improve the effectiveness of answers to questions asked to an LLM-based cybersecurity assistant. Beyond accuracy, we focus on the understandability, actionability and, most importantly, motivating power of answers, given how often users fail to follow cybersecurity recommendations. Specifically, we investigate four personalization strategies, ranging from static user profiles to interaction-history-based personalization, using a corpus of 1,045 real-world cybersecurity questions and a 7-day deployment involving 57 participants and 1,066 user questions. Across both a large-scale automated LLM-based evaluation and human evaluation, conversation-based personalization is consistently favored in comparative ratings of perceived helpfulness and likelihood of following security advice. Importantly, the relative trends observed in the LLM-based evaluation align with those obtained from human evaluation, suggesting that LLM-based evaluation can provide a scalable mechanism for comparing personalization strategies before costly user studies. These results indicate that behavior-driven personalization is a promising direction for LLM-powered cybersecurity assistants and highlight the value of combining LLM-based and human evaluation when studying personalized language-model systems. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.17839 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:56:52.834Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).