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

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening arXiv:2605.28999v1 Announce Type: cross 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 applic