Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing
A study of 180 US workers found each LLM phishing personalization level raised click-intention odds by 28%, but credibility depends on context fit.
The arXiv paper evaluates how personalized pretexts in LLM-generated spear phishing affect perceived credibility, using 180 US working adults across 1,436 evaluations of emails with four cumulative personalization levels, from workplace context to shared-project details. Convincingness rose 2.40 points per level in sensitivity analysis and click-intention odds increased 28% per level, while non-clickers shifted toward deleting rather than reporting. Qualitative coding showed details matching the recipient's role and routines supported credibility, whereas incorrect, vague, or channel-inappropriate details raised suspicion. The authors argue personalization effectiveness depends on pretext fit, with implications for workplace security training.
- 1,436 evaluations; click-intention odds rose 28% per personalization level
- Role-matching details boosted credibility; vague or wrong details raised suspicion
- Messages from named individuals referencing coworkers beat departmental senders
Full article231 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.04410