RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Topic Modelling for Humans

A frida tool to dump dex in memory to support security engineers analyzing malware.

A Coverage Explorer for Reverse Engineers

Longformer: The Long-Document Transformer

A Trace Explorer for Reverse Engineers

Code for using and evaluating SpanBERT.

a bert for retrieval and generation

IPython console integration for IDA Pro

An Interactive Hex-Rays Microcode Explorer

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

IDAPython plugin that synchronizes disassembler and decompiler views

BERT for Coreference Resolution

A grammar based feedback Fuzzer

IDAPyHelper is a script for the Interactive Disassembler that helps writing IDAPython scripts and plugins.

A parser of Windows Defender's DetectionHistory forensic artifact, containing substantial info about quarantined files and executables.

This is the official repository for VulHawk.

Convert Microsoft Defender Antivirus Signatures (VDM) into YARA rules

Full implementaion of Genius

长文本相似度模型

lazy_dataset: Process large datasets as if it was an iterable.

Official implementation for UniASM: Binary Code Similarity Detection without Fine-tuning.

Custom Iterable Dataset Class for Large-Scale Data Loading

🐳 PyLoader: An asynchronous Python dataloader for loading big datasets, supporting PyTorch and TensorFlow 2.x.

Extract the emulated files in Windows Defender signature database