Sign Up Wallet a Block Chain based Personally Identifiable Information (PII) Masking using Lookup Substitution

Digital identity is a user’s online identification, similar to a physical identification card such as a passport or driver’s license. A digital identity contains characteristics or attributes of the user. As we access apps and websites, organizations are dominantly using centralized and federated identity management systems (e.g. signing in with a Google or Facebook account) by default. The centralized system puts data at risk of large scale hacks and breaches while the federated model enables companies to track user data without their knowledge. Existing identity management systems either use a centralized authentication server or rely on identity providers to authenticate users for gaining access to various services. These systems have failed to safeguard user data privacy and do not encourage the portability of identity data. A trustworthy and reliable system is needed so that individuals can interact and network digitally and securely. These problems are motivated the development of the Sign Up Wallet a blockchain and machine learning based Self-Sovereign Identity model to manage digital identities. The emerging blockchain technology enables self-sovereign identity management, a decentralized identity management model that eliminates identity providers as a trusted third party and machine learning is used to find the trusted service provider. In this proposed system users store their digital identity in a Sign Up Wallet with cryptographic keys. When registering with a trusted service provider, a Unique Personal Identifier (UPI) Code is submitted for direct credential verification. Logistic Regression is used for predicting whether a website is trusted or not. If the service provider is untrusted, a masked credential is generated using a Lookup Substitution Algorithm, preserving privacy during verification. This masked credential is then provided to the service provider, allowing verification without exposing the raw data and maintaining user security