paperMay 2026Unreviewed

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

Mohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang, Neil Zhenqiang Gong, Tianlong Chen, Dawn Song

Abstract

LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studies. Its prevalence and impact in real-world LLM-based applications are largely unexplored. In this work, we present the first systematic study of prompt-injection attacks in a widely used application: LLM-based resume screening. Our analysis is based on approximately 200K real-world resumes collected over multiple years

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{zhang2026measuring,
  title = {{Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening}},
  author = {Mohan Zhang and Yuqi Jia and Zhen Tan and Steven Jiang and Neil Zhenqiang Gong and Tianlong Chen and Dawn Song},
  year = {2026},
  month = may,
  eprint = {2605.28999},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.28999}
}