Welcome to shieldtext

shieldtext  is an innovative AI-powered technology that uses a large language model (LLM) in social networks and messaging apps to filter offensive messages using an artificial intelligence that the users can customize. 

We tested our technology with real examples of offensive comments from TikTok and Instagram. These offensive comments were not blocked by the text moderation used by these two social networks, whereas our technology did. As a result, we can state that our AI technology, based on a customized use of a large language model (LLM), is more effective than the solutions implemented by these two social networks.

shieldtext introduces a Messaging System that integrates advanced AI to:

• ✅ Filter offensive messages in real time without compromising privacy.
• ✅ Protect minors under 16 by applying mandatory AI-filters.
• ✅ Apply shadow banning to toxic users without them perceiving it.
• ✅ Prevent the use of violent or explicit images in profiles.