Protect your machine learning models easily and securely with watermarking 🔑
-
Updated
Apr 24, 2024 - Python
8000
Protect your machine learning models easily and securely with watermarking 🔑
This is the code of ICLR 2022 Oral paper 'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization'.
Secure boot loader for MAX78000
Demo for distributed co-simulation using UniFMU
SERP VPN - A Proxy browser Extension to help hide your IP and protects your privacy on your web browser — even on unsecured Wi-Fi.
This is a governed agentic workflow with HITL for 3rd Party Data Migration
IP protection using differential privacy
A shows bottlenecks in human only workflows while B is for agentic and HITL workflows to ensure accountability and to prevent automation bias
Reference typescript library for OpenSig blockchain signatures
This sample workflow is designed to show how agents can migrate tax data in a way that is compliant with new regulations and include HITL.
SAMPLE of how deterministic guardrails fit with Human-in-the-loop safety controls. This is NOT a complete workflow! DO NOT USE!
This is a SAMPLE of how roles can be used to give the LLM a sense of self and to help it identify the users purpose and ensure greater governance over actions
OpenSig protocol specification
This is a workflow for an AI hiring portal with governance that achieves regulatory compliance through HITL
LLM Deterministic Guardrails w/o proprietary information included - SAMPLE ONLY
A blueprint of an agentic data scraper workflow that actually thinks
Add a description, image, and links to the ip-protection topic page so that developers can more easily learn about it.
To associate your repository with the ip-protection topic, visit your repo's landing page and select "manage topics."