# Secure Multi-Party Computation (MPC) > ⚠️ **Evaluation in Progress** > > Some of the mechanisms described on this page are currently **being evaluated and validated**. They represent design options under consideration, and may be refined, replaced, or omitted as the system evolves. Nesa employs Secure Multiparty Computation (SMPC or MPC) for provable cryptographic security across the network. SMPC is a cryptographic protocol that enables multiple parties to jointly compute a function over their inputs while keeping those inputs private. Each participant in the computation has a piece of the overall data puzzle, yet none can see the other parties’ pieces. This method ensures that intermediate information remains undisclosed to any participating party throughout the process, with only the final output being revealed to the designated recipient. On Nesa, this is crucial for tasks where both data privacy and collaboration are necessary. However, due to the intensive computational requirements generally associated with SMPC, we have optimized its application to be restricted to lightweight tasks throughout the network. This selective application allows us to benefit from the strong provable cryptographic security guarantees of SMPC where it matters most, without overwhelming the system with undue computational processing demands. As a result, our project not only adheres to rigorous security standards but also maintains a high level of practicality and performance efficiency when handling the strictest data confidentiality measures. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/privacy-technology/secure-multi-party-computation-mpc.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.