ebagdasa

backdoors101

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

backdoor_federated_learning

Source code for paper "How to Backdoor Federated Learning" (https://arxiv.org/abs/1807.00459)

federated_adaptation

Salvaging Federated Learning by Local Adaptation

multimodal_injection

pytorch-privacy

simple Differential Privacy in PyTorch

differential-privacy-vs-fairness

Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19

propaganda_as_a_service

Code for paper: "Spinning Language Models: Risks of Propaganda-as-a-Service and Countermeasures"

backdoored_transformers

mithridates

Measure and Boost Backdoor Robustness

adversarial_illusions

Code for "Adversarial Illusions in Multi-Modal Embeddings"

location-heatmaps

slack-outlook

backdoor-learning-resources

A list of backdoor learning resources

federated

A collection of Google research projects related to Federated Learning and Federated Analytics.

federated_homework

CS5436/INFO5303 HW 5, Federated Learning part

AncilePhoneSpecStudy-iOS

ebagdasa.github.io

website

eeg-analysis

Small project to analyze eeg

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

experiments

hacl-star

HACL*, a formally verified cryptographic library written in F*

hat

Overcoming catastrophic forgetting with hard attention to the task

immersive_workshop

instacart

ipython

Official repository for IPython itself. Other repos in the IPython organization contain things like the website, documentation builds, etc.

models

Models and examples built with TensorFlow

myscrapper

pow_assent

Multi-provider authentication for your Pow enabled app

RestrictedPython

A restricted execution environment for Python to run untrusted code.

rnnse