Official PyTorch implementation of ICS-PhysGAN: Generating High-Fidelity Zero-Day Industrial Attacks using Physics-Constrained Adversarial Learning (WGAN-GP) on the SWaT dataset.
-
Updated
Feb 25, 2026 - Python
Official PyTorch implementation of ICS-PhysGAN: Generating High-Fidelity Zero-Day Industrial Attacks using Physics-Constrained Adversarial Learning (WGAN-GP) on the SWaT dataset.
A self-evolving AI-based Intrusion Detection System (AI-IDS) using Random Forest and Variational Autoencoder (VAE) for hybrid detection of known attacks and zero-day malware, with a real-time Human-in-the-Loop feedback mechanism for continuous model retraining.
Add a description, image, and links to the zero-day-attack topic page so that developers can more easily learn about it.
To associate your repository with the zero-day-attack topic, visit your repo's landing page and select "manage topics."