AI RESEARCH

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents

arXiv CS.AI

ArXi:2602.00979v2 Announce Type: replace-cross Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these grading agents operate ``in the wild'', their vulnerability to adversarial manipulation raises critical concerns about agent security and trustworthiness. In this paper, we