
ethibench
Evaluation framework for AI penetration testing agents that measures validated vulnerability discovery using LLM-based semantic matching, bipartite…

Evaluation framework for AI penetration testing agents that measures validated vulnerability discovery using LLM-based semantic matching, bipartite…

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

The agent that grows with you

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Code for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'


This repository demonstrates a machine learning pipeline for detecting MITRE ATT&CK techniques from logs and enriching the output using a local LLM.

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…

The code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"

Replicable Blueprint for advanced DDoS Purple Teaming, engineered for the threat landscape. It integrates a Red Elite Teaming offensive…

An open-source digital image forensic toolset

A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440)

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

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

Google Tensor Cracks