Edgeless Systems has announced the launch of Continuum, a  security solution that provides cloud-based "Confidential AI" services and enables sharing of sensitive data with chatbots such as ChatGTP.

Continuum AI is Edgeless Systems new framework for deploying LLMs while keeping data private. It addresses the concerns of enterprises, public sector entities, and consumers alike who are reluctant to use AI services with sensitive data due to concerns about data leaks and the potential for AI models to be further trained on their input data.

At its core, Continuum ensures that user requests (or "prompts") and the corresponding replies remain encrypted throughout within an AI service, making plaintext data inaccessible to both the AI service provider and the underlying cloud infrastructure. It also protects the often highly valuable weights of AI models in the same manner. This use of encryption means that prompts are encrypted on the client, decrypted inside Continuum workers, and encrypted before sending them back to the client. The encryption key is not accessible to the operator of Continuum and data inside the worker is protected by the Continuum OS which combines remote attestation, memory encryption and sandboxing. 

To achieve this, Continuum uses the confidential computing capabilities of Nvidia H100 GPUs in concert with cutting-edge cryptography and innovative sandboxing technology, allowing AI service providers to freely update models and code without compromising security. 

According to Edgeless Systems' CEO Felix Schuster 

"Continuum will significantly influence the generative AI market, allowing a wider range of enterprises, particularly those in regulated sectors, to confidently utilize offerings like chatbots. This product embodies our mission to enable the use of cloud services without compromising on data security or compliance."   

More Information

Continuum AI

Related Articles

EdgelessDB - Taking Database Security To The Next Level