
standalone_tdo
Extracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…

Extracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Research code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational…

Fast and accurate AI powered file content types detection

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

The Python Code Tutorials

Reverse Engineering: Decompiling Binary Code with Large Language Models

An open-source digital image forensic toolset

Self-hostable AI SOC that fuses security alerts, auto-triages via agentic AI, runs MITRE ATT&CK investigations, and logs every agent decision in a…

Defeating Google's audio reCaptcha with 85% accuracy.

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

GyoiThon is a growing penetration test tool using Machine Learning.



Protection against Model Serialization Attacks