Build software better, together

trailofbits / PrivacyRaven

Privacy Testing for Deep Learning

python machine-learning privacy deep-learning model-extraction privacy-enhancing-technologies model-inversion privacy-preserving-machine-learning membership-inference

Updated Sep 5, 2025
Python

DescartesResearch / TeaStore

Star

A micro-service reference test application for model extraction, cloud management, energy efficiency, power prediction, single- and multi-tier auto-scaling

benchmark performance microservice model-extraction

Updated Jan 8, 2025
Java

dmitrykazhdan / MARLeME

Star

General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems

library reinforcement-learning rl model-extraction lime plug-and-play interpretability reinforcement-learning-agent open-ai abstract-argumentation explanations xai multi-agent-reinforcement-learning open-ai-gym knowledge-extraction explainability marl model-extractor extracting-interpretable-models

Updated May 10, 2020
C++

nclarius / pyPL

Sponsor

Star

Analytic tableau based minimal model generator, model checker and theorem prover for first-order logic with modal extensions

proof logic first-order-logic model-checking propositional-logic model-checker model-extraction modal-logic theorem-prover intuitionistic-logic predicate-logic classical-logic analytic-tableaux model-generation

Updated Jul 5, 2026
Python

dmitrykazhdan / MEME-RNN-XAI

Star

MEME: Generating RNN Model Explanations via Model Extraction

time-series recurrent-neural-networks rnn mimic-iii model-extraction concept-extraction interpretability model-explanation explainable-ai xai concept-explanation

Updated Jan 7, 2021
Jupyter Notebook

typesafehub / fdp-tensorflow-python-examples

Star

Simple machine learning in Python/Tensorflow with model saving

machine-learning tensorflow keras model-extraction

Updated Jul 27, 2017
PureBasic

qwqoro / ML-Talk

Star

📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools

conference talk model-extraction fast-track conference-talk model-inversion black-box-model adversarial-examples adversarial-attacks talk-slides black-box-attacks model-inversion-attacks attack-model model-attack talk-notes evasion-attack evasion-attacks talk-materials model-inversion-attack

Updated May 23, 2023
Jupyter Notebook

tsaglam / EcoreMetamodelExtraction

Star

Ecore metamodel reverse engineering: Automatically extract EMF metamodels from Java code.

java emf eclipse reverse-engineering eclipse-plugin metamodel eclipse-ide jdt model-driven-development ecore ecore-metamodel dynamic-emf model-extraction metamodel-extraction ecore-metamodel-extraction ecore-metamodel-reverse-engineering

Updated Feb 12, 2022
Java

dmitrykazhdan / CME

Star

CME: Concept-based Model Extraction

model-extraction concept-extraction xai interpretable-machine-learning explainability concept-explanation

Updated Nov 24, 2020
Python

lin-tan / disguide

Star

For our AAAI23 paper "DisGUIDE: Disagreement-Guided Data-Free Model Extraction" (Oral Presentation) by Jonathan Rosenthal, Eric Enouen, Hung Viet Pham, and Lin Tan.

security reverse-engineering model-extraction trustworthy-ai model-extraction-attack

Updated Feb 6, 2023
Python

springli07 / awesome-cryptanalytic-extraction

Star

A curated bilingual list of cryptanalytic neural-network model extraction papers, code, taxonomies, and open problems.

cryptanalysis neural-networks awesome-list model-extraction machine-learning-security hard-label model-stealing cryptanalytic-extraction

Updated Sep 30, 2026
Python

Marich is a model-agnostic extraction algorithm. It uses a public data to query a private model, aggregates the predicted labels, and construct a distributionall equivalent/max-information leaking extracted model.

privacy model-extraction active-learning privacy-attacks

Updated Oct 27, 2023
Jupyter Notebook

ais-climber / a-la-mode

Star

A neural network model builder, leveraging a neuro-symbolic interface.

hebbian-learning model-extraction modal-logic knowledge-representation model-building conditional-logic neuro-symbolic-ai

Updated Aug 17, 2023
Python

5h4d0wn1k / ai5-model-extract

Star

Model extraction attack toolkit that reconstructs black-box models through API queries.

machine-learning cybersecurity educational offensive-security model-extraction security-research ai-security adversarial-ml llm ml-security

Updated Sep 22, 2026
Python

roselis-lab / POC-Banking-ML-Attacks

Star

Minimal reproducible PoC of 3 ML attacks (adversarial, extraction, membership inference) on a credit scoring model. Includes pipeline, visualizations, and defenses

cybersecurity credit-scoring model-extraction adversarial-attacks membership-inference-attack mlsecops ml-security

Updated Jun 17, 2025
Python

Krishita17 / blindaudit

Star

Developer blind to the probes, auditor blind to the weights: a sealed-room protocol to audit AI models you can't steal. TEE + attestation + weight commitment + transparency log + extraction detector + DP noise + dual-signed transcript.