TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub 红队武器库🚨

TGINSIGHT SIMILAR POSTS

查找相似内容

Source channel @githubredteam · Post #84667 · 5月18日

🚨 GitHub 监控消息提醒 🚨发现关键词:#漏洞#验证#检测#分析 📦项目名称:LLM-MultiAgent-StackOverflow-Detector 👤项目作者:uguj 🛠开发语言: Python ⭐Star数量: 0 | 🍴Fork数量: 0 📅更新时间: 2026-05-18 10:51:12 📝项目描述: 基于ReAct范式的多智能体栈缓冲区溢出检测框架,用于C/C++代码漏洞分析。 - Finder Agent:基于libclang的AST解析,识别危险函数调用 - Tracer Agent:语法树回溯,分析参数可控性 - Hypothesis Agent:调用Qwen2.5-Coder大语言模型生成智能漏洞假设 - Verifier Agent:通过angr符号执行与objdump静态匹配进行二进制验证 框架形成“发现→追踪→假设→验证→反馈”的闭环检测流程。 本仓库包含毕业设计《基于大语言模型的栈溢出漏洞检测研究》的全部源代码、测试用例及实验结果。 🔗点击访问项目地址

Results

找到 1 条相似帖子

搜索 #convolution

当前筛选 #convolution清除筛选
GitHub Trends

@githubtrending · Post #14659 · 2025/05/01 15:30

#cplusplus#arm#convolution#deep_learning#embedded_devices#llm#machine_learning#ml#mnn#transformer#vulkan#winograd_algorithm MNN is a lightweight and efficient deep learning framework that helps run AI models on mobile devices and other small devices. It supports many types of AI models and can handle tasks like image recognition and language processing quickly and locally on your device. This means you can use AI features without needing to send data to the cloud, which improves privacy and speed. MNN is used in many apps, including those from Alibaba, and supports various platforms like Android and iOS. It also helps reduce the size of AI models, making them faster and more efficient. https://github.com/alibaba/MNN