
bordair-multimodal
Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain…


Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

Python framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…

Cyber Threat Defense World Modeling

A Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…

An ML powered Graph-Based Multi-Architecture Approach for ROP Gadget Detection

DGA-generated domain detection using deep learning models

Self-hosted multi-agent environment for Go with LLM-powered pentesting agents (exploiter, reverser, threathunter, webscanner) that automate…

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

NotebookLM on steroids — purpose-built for security researchers.

Reverse Shell Detection with Machine Learning

Framework for implementing Network Intrusion Detection Systems (NIDS) aimed at identifying anomalies in network flows using Federated Learning models.

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Human-evaluated benchmark for assessing LLM performance on real-world vulnerability identification, explanation, and remediation across 15+ languages…