[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text
-
Updated
Jan 11, 2025 - Python
[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text
OfflineAI is an artificial intelligence that operates offline and uses machine learning to perform various tasks based on the code provided. It is built using two powerful AI models by Mistral AI.
Local RAG system with a built-in governance agent that filters sensitive or restricted information with separated agent logging systems to keep privacy and security
[ICCV 2025] Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data matching the description.
The LLM Unlearning repository is an open-source project dedicated to the concept of unlearning in Large Language Models (LLMs). It aims to address concerns about data privacy and ethical AI by exploring and implementing unlearning techniques that allow models to forget unwanted or sensitive data. This ensures that AI models comply with privacy.
🔒 Detect security leaks in AI-assisted codebases. Static analysis tool for Python & JS/TS with cross-file taint tracking.
Semantic PII Masking & Anonymization for LLMs (RAG). GDPR-compliant, reversible, and context-aware. Supports LangChain & OpenAI
🤖 Build your own local Retrieval-Augmented Generation system for private, offline AI memory without ongoing costs or data privacy concerns.
TZDC - A Python library for privacy-enhancing data operations using cryptographic fragmentation and temporal key expiration.
Add a description, image, and links to the ai-privacy topic page so that developers can more easily learn about it.
To associate your repository with the ai-privacy topic, visit your repo's landing page and select "manage topics."