CleverHans Lab

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.

cleverhans

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

dataset-inference

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

DeCaPH

entangled-watermark

machine-unlearning

model-extraction-iclr

Proof-of-Learning

unrolling-sgd

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

verifiable-unlearning

cleverhans-lab/cleverhans

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

cleverhans-lab/machine-unlearning

cleverhans-lab/Proof-of-Learning

cleverhans-lab/entangled-watermark

cleverhans-lab/dataset-inference

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

cleverhans-lab/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.

cleverhans-lab/unrolling-sgd

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

cleverhans-lab/verifiable-unlearning

cleverhans-lab/model-extraction-iclr

cleverhans-lab/DeCaPH

cleverhans-lab/Zest-Model-Distance

cleverhans-lab/DatasetInferenceForSelfSupervisedModels

cleverhans-lab/deepfake_attribution

cleverhans-lab/ssl-attacks-defenses

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

cleverhans-lab/capc-demo

capc-demo

cleverhans-lab/FRAUD-Detect

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

cleverhans-lab/Gradients-Look-Alike-Sensitivity-is-Often-Overestimated-in-DP-SGD

cleverhans-lab/huggingface-transformers

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

cleverhans-lab/FairFeedbackLoops

cleverhans-lab/Forging

cleverhans-lab/monte-carlo-adv

cleverhans-lab/private-multi-winner-voting

New privacy-preserving mechanisms for multi-label classification.

cleverhans-lab/PrivatePrompts

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

cleverhans-lab/Confidential-PROFITT

cleverhans-lab/capc-privacy

CaPC with privacy only and without private inference.

cleverhans-lab/impartiality_viz

cleverhans-lab/ml_reg_games

cleverhans-lab/practical-attacks-against-pol

cleverhans-lab/SAT-selective-cls

Self-Adaptive Traning for Selective Classification.

cleverhans-lab/sc-nntd