University of Southern California（南加州大学）

Agent Audit: A Security Analysis System for LLM Agent Applications

代理审计：用于大语言模型代理应用的安全分析系统

Haiyue Zhang, Yi Nian, Yue Zhao

机构 * University of Southern California（南加州大学） 纠错

AI总结 本文提出Agent Audit系统，用于检测LLM代理应用中的安全漏洞，通过数据流分析、凭证检测等方法，提高召回率并保持快速扫描速度。

Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud Detection

基于强化学习的超启发式超参数优化的公平可解释性脉冲神经网络金融欺诈检测

Sadman Mohammad Nasif, Md Abrar Jahin, M. F. Mridha

机构 * organization= Department of Computer Science \& Engineering, Khulna University of Engineering \& Technology (KUET) , city= Khulna , postcode= 9203 , country= Bangladesh ； organization= Thomas Lord Department of Computer Science, Viterbi School of Engineering, University of Southern California , city= Los Angeles , state= CA , postcode= 90089 , country= USA ； organization= Department of Computer Science, American International University-Bangladesh (AIUB) , city= Dhaka , postcode= 1229 , country= Bangladesh 纠错

AI总结 本文提出结合脉冲编码网络与强化学习引导超启发式优化器的框架，用于实现公平且可解释的脉冲神经网络金融欺诈检测，通过在Bank Account Fraud数据集上验证，模型在5%的假阳性率下达到90.8%的召回率。

Journal ref Knowledge-Based Systems (2026)