Future of Life Institute

FLI describes itself as a non-profit whose mission is to steer transformative technology towards benefiting life and away from extreme, large-scale risks S-3611. Its verification work includes:

• With Mithril Security, FLI built a secure-hardware proof of concept on Intel SGX and the BlindAI framework in which a model owner leases weights to an untrusted party S-1203. It was designed to keep the weights inaccessible to the borrower, report how much computing is done and provide an off-switch S-1203. FLI calls it "not necessarily deployable as is", citing performance and hardware attacks that need mitigation S-1203. See TEE remote attestation for AI workloads.
• A 2024 FLI post with Mithril Security reports AICert, a proof of concept in which Trusted Platform Modules bind a model's weights to the code and data used to train it S-3381. The authors state that it covers fine-tuning only, has not been audited by a third party and does not detect poisoned models or datasets S-3381.
• The AI Futures Project's verification page lists FLI and SASH as building a confidential network logger prototype S-1511, and SASH names FLI as an early partner in that work S-1320. See SASH confidential network logger.