cleverhans-lab Goto Github PK

capc-demo

capc-demo

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.

capc-privacy

CaPC with privacy only and without private inference.

cleverhans

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

confidential-profitt

dataset-inference

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

datasetinferenceforselfsupervisedmodels

decaph

deepfake_attribution

entangled-watermark

fairfeedbackloops

forging

fraud-detect

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

gradients-look-alike-sensitivity-is-often-overestimated-in-dp-sgd

huggingface-transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

impartiality_viz

machine-unlearning

ml_reg_games

model-extraction-iclr

monte-carlo-adv

practical-attacks-against-pol

private-multi-winner-voting

New privacy-preserving mechanisms for multi-label classification.

privateprompts

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

proof-of-learning

rsa-byzantine

sat-selective-cls

Self-Adaptive Traning for Selective Classification.

sc-nntd

ssl-attacks-defenses

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

unrolling-sgd

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

verifiable-unlearning