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

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

A curated collection of adversarial attack and defense on graph data.

Cisco Config Analysis Tool

h2t (HTTP Hardening Tool) scans a website and suggests security headers to apply

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"

[NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

A certifiable defense against adversarial examples by training neural networks to be provably robust

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

Emulate and Dissect MSF and *other* attacks

A Cyber Range to learn hacking (both attacking & defending) techniques locally in your computer

The Web Armory | Web武器库

SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression

Feature Scattering Adversarial Training (NeurIPS19)

A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.

This is the official pytorch implementation for paper: IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

An application to catch, search and analyze HTTP secure headers.

[ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

Deauthalyzer is a script designed to monitor WiFi networks and detect deauthentication attacks. It utilizes packet sniffing and analysis techniques to identify deauthentication attack packets and provide relevant information about the attack.

[ICML 2019] ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation