仓库/Skill 库

基于 Base 的 fail-closed 支付安全判定：识别已知恶意钱包、高度相似 token 及反复 rug 的资方。非托管、仅依赖描述符——工具本身不转移资金。Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders. Non-custodial, descriptor-only — no tool moves funds.

大语言模型监督微调的反馈对齐方法Feedback alignment for supervised fine-tuning of large language models

💳 使用 XGBoost 检测金融交易欺诈，结合针对不平衡数据集与复杂特征的高级优化技术💳 Detect fraudulent financial transactions using XGBoost. Optimize performance with advanced techniques for imbalanced datasets and complex features.

一个可复现的研究原型，针对漂移感知欺诈检测，采用 actor-critic 强化学习、动态特征重加权与自适应回放，应对交易分布的持续演化A reproducible research prototype for drift-aware fraud detection using actor-critic reinforcement learning, dynamic feature reweighting, and adaptive replay under evolving transaction distributions.

应用型 AI 网络安全研究实验室，涵盖机器学习威胁检测、对抗机器学习、鲁棒性、网络威胁情报、MITRE ATT&CK/ATLAS、LLM 安全与可复现研究。Applied AI Cybersecurity research labs covering machine learning threat detection, adversarial ML, robustness, cyber threat intelligence, MITRE ATT&CK/ATLAS, LLM security and reproducible research.

用于探索 LLM Security 新兴研究主题的研究路线图与文献综述仓库。A research roadmap and literature review repository for exploring emerging research topics in Large Language Model Security.

活文献综述：面向网络安全领域的现代数据架构Living literature review: Modern data architecture for cybersecurity

通过硬件 IP 核在硅层级抑制 LLM 幻觉，强制 LLM 输出的语义完整性Enforce semantic integrity in LLM outputs with a hardware IP core that suppresses hallucinations at the silicon level

系统综述材料：研究方案、PRISMA 记录、各研究的数据以及筛选决策。Systematic review materials: protocol, PRISMA records, per-study data, screening decisions

关于细菌抗生素耐药程度标准化定义使用的系统综述与建议A systematic review and recommendations on the use of standard definitions for extent of antibiotic resistance in bacteria

AI 助手的安检守卫。检查 AI 尝试调用的每一个工具，防止数据泄露与未授权命令。A security guard for AI assistants. It checks every tool an AI tries to use, preventing data leaks and unauthorized commands.

专注于通过统计分析与机器学习模型检测金融欺诈的数据科学研究项目。Data science research project focused on detecting financial fraud through statistical analysis and machine learning models.

一个研究级 Python 流水线，用于分析 Wireshark 抓包数据，提取网络流特征，进行统计分析、异常检测，并生成可用于 GAN 入侵检测系统的机器学习就绪数据集A research-grade Python pipeline for analyzing Wireshark packet captures, extracting network flow features, performing statistical analysis, anomaly detection, and generating machine learning-ready datasets for GAN-based Intrusion Detection Systems.

一项系统性文献综述A systematic literature review

监管 AI 的系统文献综述。Systematic Literature Review for Regulatory AI