
HDI-GraphRAG-Attack
Research implementation of Hop-Decayed Influence (HDI) and the 3S attack framework, exposing structural auxiliary indexing vulnerabilities in…

Research implementation of Hop-Decayed Influence (HDI) and the 3S attack framework, exposing structural auxiliary indexing vulnerabilities in…

Refusal localizes, the damage relocates, safety layers under few-sample fine-tuning

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

Web-based adversary emulation platform that orchestrates Atomic Red Team tests across Windows endpoints via Go agents, with MITRE ATT&CK mapping, APT…

Build guide for Red Teaming home lab. GOAD lab setup in Proxmox and pfSense, Operator/C2 and Redirectors.

Benchmarking prompt injection detections for web agents.

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

The exploit server for out-of-band findings. Point a target at a domain you own. Every HTTP request and every email it sends back lands in a…

Research implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…

An adversarial example library for constructing attacks, building defenses, and benchmarking both

A security scanner for your LLM agentic workflows

Curated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…

Train, evaluate, and explore neural networks with built-in adversarial robustness tools, including PGD attacks, adversarial training, and robust…

Threadless Process Injection using remote function hooking.

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

:cloud: :zap: Granular, Actionable Adversary Emulation for the Cloud

Clusters and elements to attach to MISP events or attributes (like threat actors)

C2 profile for Mythic tunneling encrypted peer-to-peer agent traffic through IEEE 802.1AB LLDP Organizationally Specific TLVs for covert Layer 2…