arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.12583cs.CRcs.AI
收藏

使用分类器检测应用于应用程序中的提示注入攻击

Detecting Prompt Injection Attacks Against Application Using Classifiers

Department of Computer Science (CS)(计算机科学系);Department of Computer Science and Engineering (CSE)(计算机科学与工程系);School of Data and Sciences (SDS)(数据与科学学院)

Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid, Md. Abrar Faiaz Khan, Md. Omar Faruk, Yaseen Nur

AI总结:

本研究通过训练多种分类器,旨在检测网络应用中的提示注入攻击,提升系统安全性和稳定性。

摘要:

提示注入攻击可能会破坏关键系统的安全性和稳定性,从基础设施到大型网络应用。本工作基于HackAPrompt Playground提交语料库整理和扩展了提示注入数据集,并训练了几种分类器,包括LSTM、前馈神经网络、随机森林和朴素贝叶斯,以检测LLM集成网络应用中的恶意提示。所提出的方法提高了提示注入检测和缓解能力,有助于保护目标应用和系统。

英文摘要:

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection and mitigation, helping protect targeted applications and systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑