ainewsblitz.com

Breaking

Study Finds Hidden Prompt Injections in About 1% of Résumés Aimed at Fooling AI Screeners

Study Finds Hidden Prompt Injections in About 1% of Résumés Aimed at Fooling AI Screeners
  • Security
  • Recruiting & HR
  • Research & Papers

A growing number of job seekers are embedding invisible instructions in their résumés to manipulate AI-based hiring tools, according to a large-scale study by Duke University researchers that examined roughly 200,000 real submissions. The findings, detailed in a paper slated for presentation at the USENIX Security Symposium 2026, mark one of the first empirical measurements of prompt injection attacks in the wild for résumé screening.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year