Privacy Testing for Deep Learning
-
Updated
Sep 5, 2025 - Python
Privacy Testing for Deep Learning
Analytic tableau based minimal model generator, model checker and theorem prover for first-order logic with modal extensions
For our AAAI23 paper "DisGUIDE: Disagreement-Guided Data-Free Model Extraction" (Oral Presentation) by Jonathan Rosenthal, Eric Enouen, Hung Viet Pham, and Lin Tan.
CME: Concept-based Model Extraction
A neural network model builder, leveraging a neuro-symbolic interface.
Minimal reproducible PoC of 3 ML attacks (adversarial, extraction, membership inference) on a credit scoring model. Includes pipeline, visualizations, and defenses
Model Reconstruction from Counterfactual Explanations
Comprehensive model extraction attack
Add a description, image, and links to the model-extraction topic page so that developers can more easily learn about it.
To associate your repository with the model-extraction topic, visit your repo's landing page and select "manage topics."