cleverhans-lab/private-multi-winner-voting

Stars
1
Language
Python
License
MIT License
Created about 2 years ago
Updated almost 2 years ago

cleverhans-lab/private-multi-winner-voting

cleverhans-lab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

New privacy-preserving mechanisms for multi-label classification.

cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Jupyter Notebook

machine-unlearning

entangled-watermark

Proof-of-Learning

dataset-inference

[ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning

Jupyter Notebook

capc-iclr

CaPC is a method that enables collaborating parties to improve their own local heterogeneous machine learning models in a setting where both confidentiality and privacy need to be preserved to prevent explicit and implicit sharing of private data.

unrolling-sgd

code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22

verifiable-unlearning

model-extraction-iclr

DeCaPH

deepfake_attribution

Zest-Model-Distance

DatasetInferenceForSelfSupervisedModels

capc-demo

Jupyter Notebook

FRAUD-Detect

Official implementation of Washing The Unwashable : On The (Im)possibility of Fairwashing Detection, NeurIPS 2022

ssl-attacks-defenses

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

Gradients-Look-Alike-Sensitivity-is-Often-Overestimated-in-DP-SGD

Forging

Jupyter Notebook

monte-carlo-adv

FairFeedbackLoops

PrivatePrompts

Code for the differential learning algorithms for soft and discrete prompts.