Log4Shell-vulnerability-CVE-2021-44228-

Detección de amenazas Log4Shell CVE-2021-44228 Descripción general Este repositorio proporciona un análisis en profundidad y la implementación de un sistema de detección de amenazas Log4Shell CVE-2021-44228 basado en aprendizaje automático Machine Learning. Incluye: Comprender Log4Shell : qué es ...

AI-driven-MITRE-Attack

POC : Detección de Tácticas MITRE y Enriquecimiento de Alertas Impulsado por IA Este repositorio demuestra un pipeline de aprendizaje automático para detectar técnicas MITRE ATT&CK a partir de registros y enriquecer la salida usando un LLM local. Descripción general El proyecto está dividido en d...

guardd

guardd Detección de anomalías de comportamiento impulsada por aprendizaje automático para Linux usando eBPF + Isolation Forest Guardd recopila eventos de bajo nivel del sistema ejecución de procesos, actividad de red, los agrega en vectores de características en ventanas de tiempo y detecta...

batea

Batea Batea 是一种由木材或铁制成的大型浅盘，传统上被淘金者用来淘洗沙砾以回收金块。 Batea 是一个基于异常检测机器学习算法的上下文驱动网络设备排名框架。其目标是让安全团队能够使用 nmap 扫描报告 自动筛选出大型网络中有趣的网络资产 。我们将这些资产称为 金块 。 关于金块发现以及 Batea 背后科学的更多信息，请参见我们的白皮书这里。 工作原理 Batea 通过从 nmap 报告（XML）中构建所有设备的数值表示（numpy），然后应用异常检测方法来揭示金块。它可以通过向网络元素的数值表示添加特定特征（即有趣特性）来轻松扩展。...

ranger

ranger A tool to support security professionals access and interact with remote Microsoft Windows based systems. This project was conceptualized with the thought process, we did not invent the bow or the arrow, just a more efficient way of using it. Ranger is a command-line driven attack and...

CVE-2020-0665

CVE-2020-0665 - Bypass de Filtro SID Prueba de Concepto para CVE-2020-0665, que permite eludir el Filtrado SID en Bosques de Active Directory Ataque entre Bosques. Requisitos para el ataque La máquina Controladora de Dominio objetivo no debe tener parches posteriores a febrero de 2020. Haber...

SysTrace

SysTrace 2.0 ptrace-based Linux syscall monitor and sandbox for analyzing ELF binaries. SysTrace runs a target inside an isolated Linux namespace environment, traces its system calls and child processes, applies rule-based detection and weighted risk scoring, then uses a Random Forest classifier ...

ThreatDetect

ThreatDetect ThreatDetect 是一个基于 Streamlit 的内部威胁检测原型，用于分析员工活动数据并标记潜在风险行为。它使用训练好的 XGBoost 分类器结合孤立森林异常检测器，生成组织级风险摘要和可解释的员工级洞察。 演示 该应用可以使用 Streamlit 本地运行。之前发布了一个部署演示，地址为： https://threatdetectcos720.streamlit.app/ 主要功能 从上传的 CSV 文件进行批量风险检测 组织威胁摘要，包含数量、概率分布和风险等级 使用 SHAP 值对每位员工进行可解释性分析...

ShielDroid: A Hybrid Approach Integrating Machine and Deep Learning for Android Malware Detection

The rapid advancement of modern technology has led to a significant increase in the use of smart devices, such as smartphones and tablets, resulting in the widespread adoption of mobile applications. Although applications are required to undergo malware screening before being published on officia...

"Warning: Exchange account was not found"

Challenge When backing up Exchange Online mailboxes, Veeam Backup for Microsoft 365 intermittently fails to discover and process some mailboxes, reporting the following warning: Warning: Exchange account was not found The affected mailboxes vary between job runs, and in some cases, only a small...

Categorical Robustness Assessment for Machine Learning Based Network Intrusion Detection Systems

Network Intrusion Detection Systems NIDS heavily utlize Machine Learning ML but ML models can be manipulated via adversarial attacks. These attacks add carefully crafted perturbations to network traffic data that leads to misclassifications. While prior work has demonstrated adversarial...

Meta-Quantum Ensemble Framework for Robust Network Intrusion Detection

Intrusion Detection Systems IDSs must maintain high detection sensitivity while operating under strict false-positive constraints, a challenge intensified by class imbalance and heterogeneous IoT traffic. This work investigates whether heterogeneous quantum learners can provide useful and...

Botnet Detection on CTU-13 Using Lightweight Machine Learning Models

Botnets are among the most persistent cyber threats, enabling large-scale attacks such as spam, credential theft, and distributed denial-of-service DDoS. While deep learning approaches have recently been applied to botnet detection, they are computationally intensive and often lack...

Detecting Data Exfiltration through I2P Anonymity Networks: A Two-Phase Machine Learning Approach

The Invisible Internet Project I2P provides strong anonymity through garlic routing and distributed network architecture, making it attractive for legitimate privacy needs. Nevertheless, the same properties can be exploited by malicious actors to steal sensitive information from corporate network...

A Comparative Analysis of Machine Learning Models for Intrusion Detection in Intelligent Transport Systems

AI-powered edge computing security is moving Intelligent Transportation Systems ITS from passive, rule-based protections to proactive, smart, zero-touch, self-sufficient safeguards that neutralize threats in milliseconds. As transportation becomes more connected with edge computing, massive IoT,...

SeqShield: A Behavioral Analysis Approach to Uncover Rootkits

Rootkits are among the most elusive types of malware, capable of bypassing traditional static analysis methods due to their metamorphic behavior. Signature-based detection techniques struggle against these threats, necessitating a shift toward dynamic analysis approaches. We propose SeqShield, a...

Russian Forest Blizzard Hackers Hijack Home Routers for Global Spying

Microsoft Threat Intelligence reveals how Russian hacking group Forest Blizzard uses home routers for DNS hijacking and spying...

Russia Hacked Routers to Steal Microsoft Office Tokens

Hackers linked to Russia's military intelligence units are using known flaws in older Internet routers to mass harvest authentication tokens from Microsoft Office users, security experts warned today. The spying campaign allowed state-backed Russian hackers to quietly siphon authentication tokens...

SOHO router compromise leads to DNS hijacking and adversary-in-the-middle attacks

In this article 1. DNS hijacking attack chain: From compromised devices to AiTM and other follow-on activity 2. Mitigation and protection guidance 3. Microsoft Defender detection and hunting guidance Executive summary Forest Blizzard, a threat actor linked to the Russian military, has been...

AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems

AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema check and still trick a user: a button might say "View invoice" while its...