MADLIRA

MADLIRA Malware detection using learning and information retrieval for Android Overview MADLIRA is a tool for Android malware detection. It consists in two components: TFIDF component and SVM learning component. In gerneral, it takes an input a set of malwares and benwares and then extracts the...

spamscanner

A spam filter for Node.js, the command line and mail servers. It catches spam, phishing, scams and malware in any language, explains every decision, and can ask a language model about close calls. spamscanner.net · Getting started · Documentation Features A classifier that reads every language...

Pesidious

Malware Mutation using Deep Reinforcement Learning and GANs The purpose of the tool is to use artificial intelligence to mutate a malware PE32 only sample to bypass AI powered classifiers while keeping its functionality intact. In the past, notable work has been done in this domain with researche...

ayaFlow

ayaFlow ayaFlow is a Rust + eBPF network traffic analyzer built with Aya. It runs one agent per Linux node, attaches a TC classifier at ingress and egress, and exposes live traffic data, historical SQLite-backed history, and Prometheus metrics. What It Does Captures IPv4, IPv6, TCP, and UDP traff...

CVE-2026-68138

CVE-2026-68138: Linux qdisc rate-table 경합을 이용한 로컬 루트 권한 상승 이 저장소에는 CVE-2026-68138 에 대한 개념 증명PoC 로컬 권한 상승 익스플로잇이 포함되어 있습니다. 이 취약점은 Linux 트래픽 제어 rate-table 코드의 경합race입니다. 테스트한 QEMU 환경에서 이 PoC는 외부 UID 1000을 가진 일반 프로세스에서 초기 사용자 네임스페이스의 UID 0 셸로 권한을 상승시킵니다. 경고 이 코드는 의도적으로 커널 힙 상태를 손상시킵니다. 소유한 격리된 일회용...

ache

ACHE Focused Crawler ACHE is a focused web crawler. It collects web pages that satisfy some specific criteria, e.g., pages that belong to a given domain or that contain a user-specified pattern. ACHE differs from generic crawlers in sense that it uses page classifiers to distinguish between...

dga_predict

LSTM을 사용한 DGA도메인 생성 알고리즘 예측 이 저장소는 도메인을 DGA 또는 정상benign으로 분류하는 매우 간단한 코드를 포함합니다. 이 코드는 arXiv 논문https://arxiv.org/abs/1611.00791의 결과를 시연합니다. 차이점 중 하나는 데이터셋입니다. 논문과 이 저장소 모두 정상 도메인으로 Alexa 상위 1백만 개를 사용하지만, 이 저장소는 단순함을 위해 자체 도메인을 생성합니다. 또한 논문의 LSTM 및 바이그램bigram 분류기만 구현했습니다. 이 둘은 가장 성능이 좋은 분류기이며 Kera...

WAF-A-MoLE

WAF-A-MoLE A guided mutation-based fuzzer for ML-based Web Application Firewalls, inspired by AFL and based on the FuzzingBook by Andreas Zeller et al. Given an input SQL injection query, it tries to produce a semantic invariant query that is able to bypass the target WAF. You can use this tool f...

bordair-detector

Bordair Detector LLM 입력에서 프롬프트 인젝션 및 제일브레이크 시도를 탐지하는 2단계 탐지기입니다. 정규식 게이트가 모델을 건드리지 않고 쉬운 대부분의 트래픽을 처리하며, 모호한 경우는 ONNX로 실행되는 양자화된 DeBERTa-v3 분류기로 넘어갑니다. 동일한 엔진이 이미지, 문서, 오디오 입력을 모두 처리하므로 어떤 채널을 통해 주입되든 탐지됩니다. Bordair Multimodal 데이터셋500,000개 이상의 레이블링된 샘플으로 훈련되었으며, 인간 플레이어가 탐지기를 이기기 위해 경쟁하는 라이브 게임에서...

SANS_THIR16

SANSTHIR16 SANS 저비용 헌팅 DGA 분류기 RandomForest는 voweltoconsonantratio, longestconsonantsequence, 사전 및 Alexa 상위 도메인의 ngrams와 같은 도메인 특징을 사용합니다. ROC 곡선...

ThreatDetect

ThreatDetect ThreatDetect is a Streamlit-based insider threat detection prototype that analyzes employee activity data and flags potentially risky behavior. It uses a trained XGBoost classifier together with an Isolation Forest anomaly detector to produce organisation-level risk summaries and...

Astra Linux – Vulnerability in Linux, Linux 5.10

In the Linux kernel, the following vulnerability has been resolved: net: sched: flower: Protect flwalk with rcu. The patch that refactored flwalk to use idrforeachentrycontinueul also removed the rcu protection for individual filters. This caused a use-after-free when the filter was deleted...

Adversarial Debiasing of Machine Learning Models for Enhanced Network Security against DDoS Attacks

Distributed Denial of Service attacks are a growing threat to network infrastructure, and new techniques, including the use of generative AI, make them harder to detect. Traditional detection systems, such as rule based firewalls, often fail to identify these evolving attack patterns. In this...

Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study across Eight Weeks

Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect directly under controlled conditions. We collected a longitudinal dataset of 40 fixed passwords, each typed four times per weekly...

A Gmail-Based Phishing Detection Prototype for Nigerian Fintech Emails Using Sender Checks and BiLSTM Classification

Phishing emails that impersonate Nigerian fintech providers can combine deceptive sender addresses, lookalike links, and locally familiar language. This study presents a Gmail browser extension that integrates sender-domain and URL checks with a bidirectional long short-term memory BiLSTM...

SUSE CVE-2026-90099

In the Linux kernel, the following vulnerability has been resolved: net/sched: account classifier filter allocations to memcg Allocations in the tc classifier change paths filter objects, per-CPU counters, and per-filter aux data use plain GFPKERNEL without GFPACCOUNT, allowing unprivileged users...

AZL-102564 CVE-2026-90248 affecting package kernel for versions less than 6.6.157.1-1

In the Linux kernel, the following vulnerability has been resolved: net/sched: clsapi: fix teardown of an adopted proto on insert-race loss In tcnewtfilter the create branch sets tpcreated = 1 before calling tcfchaintpinsertunique. When the caller loses the race another request inserted a proto a...

DEBIAN-CVE-2026-90099

In the Linux kernel, the following vulnerability has been resolved: net/sched: account classifier filter allocations to memcg Allocations in the tc classifier change paths filter objects, per-CPU counters, and per-filter aux data use plain GFPKERNEL without GFPACCOUNT, allowing unprivileged users...

PT-2026-94447

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description Unprivileged users can pin kernel memory outside of memory control group memcg charging. This occurs because allocations in the tc classifier change paths—including filter objects, per-C...

AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection

Email spam and phishing attacks remain a critical security threat. Adversaries increasingly exploit large language models to craft contextually convincing malicious messages, and existing spam detection systems often struggle to keep pace. Generalization across diverse and evolving attack scenari...