Python Poisoning Resources

plan I - Linux Fundamentals Les utilisateurs et les droits Installer des programmes avec apt-get Surveiller l'activité du système Exécuter des program

p0znMITM ARP Poisoning Tool What is ARP? Address Resolution Protocol (ARP) is a protocol or procedure that connects an ever-changing IP address to a f

Data Poisoning based on Adversarial Attacks using Non-Robust Features Usage python main.py [-h] [--gpu | -g GPU] [--eps |-e EPSILON] [--pert | -p PER

Short PhD seminar on Machine Learning Security (Adversarial Machine Learning)

FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective Official implementation of "FL-WBC: Enhan

CoProtector Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

CoProtector Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Adversarial poison generation and evaluation. This framework implements the data poisoning method found in the paper Adversarial Examples Make Strong

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.).

dnspooq DNSpooq PoC - dnsmasq cache poisoning (CVE-2020-25686, CVE-2020-25684, CVE-2020-25685) For educational purposes only Requirements Docker compo