Can AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2511.11759/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTCan AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation — mentioned by gerdesjhttps://news.ycombinator.com/item?id=45987623urn:hackerpapers:mention:2511.11759:45987623Thu, 20 Nov 2025 01:22:45 GMT<p>This is a blog post about: https://arxiv.org/pdf/2511.11759 There are more links in the post. In the abstract of that paper: &quot;In a human validation study with 108 senior vol- unteers, AI-generated phishing emails successfully compro- mised 11% of participants.&quot; The Introduction mentions: &quot;Americans aged 60 and older reported losses of nearly $4.9 billion to online fraud in 2024&quot; I would say that is a big deal.</p><p><a href="https://hackerpaper.kaipfister.de/p/2511.11759/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CR