mathsinn's starred repositories
adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
advmlthreatmatrix
Adversarial Threat Landscape for AI Systems
obfuscated-gradients
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library
counterfit
a CLI that provides a generic automation layer for assessing the security of ML models
federated-learning-lib
A library for federated learning (a distributed machine learning process) in an enterprise environment.
ai-privacy-toolkit
A toolkit for tools and techniques related to the privacy and compliance of AI models.
gard-adversarial-speaker-id
Adversarial attack and defense strategies for deep speaker recognition systems
ThymesisFlow
Memory Disaggregation on POWER9 with OpenCAPI 3.0 M1 & C1
de-identification
The Data De-Identification service provides a wide range of de-identification capabilities designed to support GDPR, HIPAA, CCPA and other privacy frameworks allowing customers to meet their regulatory and privacy requirements.
Trusted-ML-Pipelines
Trusted ML Pipeline Tutorial
devil-in-GAN
this is a repo for the demo on backdoor attacks on StyleGAN and WaveGAN
armory-example
Example external repository for interacting with armory.
pycloudmessenger
This repository includes sample code showing how to interact with messaging based services provided by IBM Research Ireland.
Musketeer-Client
Client installation for Musketeer FFL clients
integration-of-adversarial-attacks-in-training-pipeline
Use a Jupyter notebook to integrate the Adversarial Robustness Toolbox (ART) into a neural network model training pipeline with Fabric for Deep Learning to find model vulnerabilities.
ai-minimization-toolkit
A toolkit for reducing the amount of personal data needed to perform predictions with a machine learning model