Defense Python Packages

deeprobust

A pytorch adversarial library for attack and defense methods on images and graphs

mildoc-lint

Local-first linter for CUI markings, PII indicators, USMC O-SMEAC orders, naval correspondence, and NAMP/CSEC readiness records.

django-zato-plugin

ESB, SOA, REST, APIs and Cloud Integrations in Python

decoyshield

Counter-recon honeypot against agentic LLM attackers (PentestGPT/AutoGPT/LangChain). Six deploy modes: Flask drop-in, WSGI/ASGI middleware (Django/FastAPI), callable Python primitives, decoyshield CLI, edge configs (nginx/Caddy/Cloudflare), and Node.js npm package (Express/Fastify). Invisible-to-human, visible-to-LLM bait halts AI scans.

doomarena-taubench

TauBench extensions for DoomArena

doomarena

A framework to test the security and robustness of AI agents

graph-tiger

Python toolbox to evaluate graph vulnerability and robustness (CIKM 2021)

zato-testing

ESB, SOA, REST, APIs and Cloud Integrations in Python

zato-green

ESB, SOA, REST, APIs and Cloud Integrations in Python

doomarena-promptceptor

Promptceptor tool

agent-trap

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.