CleverHans Lab

All

35 repositories

confidential-guardian
Public
We show that a model owner can artificially introduce uncertainty into their model and provide a corresponding detection mechanism.
machine-learning uncertainty calibration zero-knowledge rejection abstention selective-prediction
Jupyter Notebook
•0•0•0•0•Updated Jun 2, 2025Jun 2, 2025
suitability
Public
Jupyter Notebook
•0•3•0•0•Updated May 29, 2025May 29, 2025
Secure_Noise_Sampling_DP_CL
Public
Python
•1•2•0•0•Updated May 23, 2025May 23, 2025
MLReg-PAP
Public
0•0•0•0•Updated May 12, 2025May 12, 2025
Gradients-Look-Alike-Sensitivity-is-Often-Overestimated-in-DP-SGD
Public
Python
•
MIT License
•0•3•0•0•Updated Nov 20, 2024Nov 20, 2024
FairFeedbackLoops
Public
Python
•0•1•0•0•Updated Apr 30, 2024Apr 30, 2024
cleverhans
Public
An adversarial example library for constructing attacks, building defenses, and benchmarking both
security benchmarking machine-learning
Jupyter Notebook
•
MIT License
•1.4k•6.4k•31•14•Updated Apr 10, 2024Apr 10, 2024
ml_reg_games
Public
Python
•
MIT License
•0•0•0•0•Updated Feb 7, 2024Feb 7, 2024
PrivatePrompts
Public
Code for the differential learning algorithms for soft and discrete prompts.
Python
•
MIT License
•1•1•0•0•Updated Nov 14, 2023Nov 14, 2023
machine-unlearning
Public
Python
•
MIT License
•41•193•5•0•Updated Sep 22, 2023Sep 22, 2023
DeCaPH
Public
Python
•0•7•0•0•Updated Sep 11, 2023Sep 11, 2023
DatasetInferenceForSelfSupervisedModels
Public
Python
•4•5•1•0•Updated May 4, 2023May 4, 2023
Confidential-PROFITT
Public
Java
•0•0•0•0•Updated May 3, 2023May 3, 2023
verifiable-unlearning
Public
Python
•
MIT License
•5•20•0•0•Updated Mar 20, 2023Mar 20, 2023
impartiality_viz
Public
HTML
•0•0•0•0•Updated Feb 17, 2023Feb 17, 2023
sc-nntd
Public
0•0•0•0•Updated Feb 1, 2023Feb 1, 2023
private-multi-winner-voting
Public
New privacy-preserving mechanisms for multi-label classification.
Python
•
MIT License
•0•1•0•0•Updated Dec 9, 2022Dec 9, 2022
practical-attacks-against-pol
Public
Python
•1•0•0•0•Updated Oct 27, 2022Oct 27, 2022
FRAUD-Detect
Public
Official implementation of Washing The Unwashable : On The (Im)possibility of Fairwashing Detection, NeurIPS 2022
Python
•1•4•0•0•Updated Oct 25, 2022Oct 25, 2022
dataset-inference
Public
[ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning
Jupyter Notebook
•9•32•1•0•Updated Oct 10, 2022Oct 10, 2022
monte-carlo-adv
Public
Python
•0•1•1•0•Updated Sep 20, 2022Sep 20, 2022
Forging
Public
Jupyter Notebook
•0•1•0•0•Updated Aug 25, 2022Aug 25, 2022
capc-demo
Public
capc-demo
Jupyter Notebook
•2•4•0•0•Updated Jul 24, 2022Jul 24, 2022
model-extraction-iclr
Public
Python
•
MIT License
•5•13•1•0•Updated Jul 11, 2022Jul 11, 2022
ssl-attacks-defenses
Public
On the Difficulty of Defending Self-Supervised Learning against Model Extraction
Python
•
MIT License
•0•5•0•0•Updated Jun 27, 2022Jun 27, 2022
huggingface-transformers
Public
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
•
Apache License 2.0
•30k•2•0•0•Updated May 16, 2022May 16, 2022
capc-iclr
Public
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.
Python
•
MIT License
•6•26•0•0•Updated Mar 16, 2022Mar 16, 2022
Zest-Model-Distance
Public
Python
•1•6•0•0•Updated Mar 14, 2022Mar 14, 2022
unrolling-sgd
Public
code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22
Python
•
MIT License
•2•22•0•0•Updated Mar 13, 2022Mar 13, 2022
SAT-selective-cls
Public
Self-Adaptive Traning for Selective Classification.
Python
•
MIT License
•4•0•0•0•Updated Jan 5, 2022Jan 5, 2022