A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Universal and Transferable Attacks on Aligned Language Models

A small course on exploiting and defending neural networks

LLM vulnerability scanner

A unit test-like interface for fuzzing and symbolic execution

Framework for Automating Fuzzable Target Discovery with Static Analysis. Featured at Black Hat Arsenal USA 2022.

TheftFuzzer is a tool that fuzzes Cross-Origin Resource Sharing implementations for common misconfigurations.

Python Script to Check IP Against Blacklist

A machine learning based social media pen-testing tool

Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"