Metraipolis › archive › dc_2bb95ed5117b
Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing — arXiv:2609.04410
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04410
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:51:13.840Z
- SHA-256 of the archived text
a56c5517eeed5dfe282b9cfc30438616c631541a319117966efce8f79d4aa1ee- Stable URL of this page
https://metraipolis.com/documento/dc_2bb95ed5117b
How to cite
Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing — arXiv:2609.04410 — arXiv (en), https://arxiv.org/abs/2609.04410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bb95ed5117b (Metraipolis archive dc_2bb95ed5117b, sha256 a56c5517eeed5dfe282b9cfc30438616c631541a319117966efce8f79d4aa1ee)
BibTeX
@misc{dc2bb95ed5117b,
title = {Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing — arXiv:2609.04410},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04410},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bb95ed5117b; sha256 a56c5517eeed5dfe282b9cfc30438616c631541a319117966efce8f79d4aa1ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can insert workplace details into phishing pretexts at low cost, but those details may either support or undermine a message's credibility. We recruited 180 U.S. working adults to evaluate simulated, AI-generated phishing emails in a disclosed survey. The emails used four cumulative levels of information: workplace (Level 1); recipient name and job title; job responsibilities; and coworker/shared-project context (Level 4). Participants rated each message's convincingness from 0 to 100, chose one stated action (open the link, investigate, delete, or report), and explained why their highest- and lowest-rated messages stood out. Across 1,436 valid evaluations, convincingness increased by 2.40 points per personalization level in a sensitivity analysis, while the odds of expressing click intention increased by 28\% per level. Among participants who did not express an intention to click, investigation remained common, reporting declined, and deletion increased. A post-hoc descriptive analysis found higher ratings and click intention for messages from a named person who referenced a supplied coworker than for messages from a department or entity. Qualitative coding showed why added detail could help or hurt: details that matched participants' roles and routines supported credibility, while incorrect, vague, or channel-inappropriate details raised suspicion. Together, the results highlight that personalization is not simply a matter of adding more details: it depends on whether the pretext fits the recipient's work context. We discuss how this distinction can inform workplace cybersecurity training. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.04410 — 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 2026-10-16T22:30:54.301Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).