CAFE
Data protection mechanism
An approach to prevent data leakage in distributed machine learning models by shielding sensitive information during the training process.
21 stars
1 watching
6 forks
Language: Python
last commit: over 3 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 git-disl/lockdown | A backdoor defense system for federated learning, designed to protect against data poisoning attacks by isolating subspace training and aggregating models with robust consensus fusion. | 18 |
 dcalab-unipv/turning-privacy-preserving-mechanisms-against-federated-learning | This project presents an attack on federated learning systems to compromise their privacy-preserving mechanisms. | 8 |
 eric-ai-lab/fedvln | An open-source implementation of a federated learning framework to protect data privacy in embodied agent learning for Vision-and-Language Navigation. | 13 |
 mithril-security/bastionlab | Enables secure data collaboration between data owners and scientists without exposing original data. | 170 |
 lpomfrey/django-debreach | Protects against a specific web-based attack by modifying the length of HTML responses. | 75 |
 ai-secure/dba | A tool for demonstrating and analyzing attacks on federated learning systems by introducing backdoors into distributed machine learning models. | 179 |
 mbilalzafar/fair-classification | Provides a Python implementation of fairness mechanisms in classification models to mitigate disparate impact and mistreatment. | 190 |
 tf-encrypted/moose | A secure distributed dataflow framework for encrypted machine learning and data processing | 59 |
 safe-graph/dgfraud | A toolbox for building and comparing graph neural network-based fraud detection models | 698 |
 cossacklabs/acra | Database security suite with field-level encryption, search through encrypted data, SQL injections prevention and intrusion detection capabilities. | 1,368 |
 directdefense/superserial | A Burp Suite Extender to identify Java Deserialization vulnerabilities in client requests and server responses. | 9 |
 jeremy313/soteria | An implementation of a defense against model inversion attacks in federated learning | 55 |
 dalmatinerdb/dproto | A protocol defining data exchange formats for a specific relational database system. | 1 |
 protectai/llm-guard | A security toolkit designed to protect interactions with large language models from various threats and vulnerabilities. | 1,296 |
 ybdai7/chameleon-durable-backdoor | A federated learning system implementation that enables planting durable backdoors in global models by adapting to peer images. | 34 |