{
  "schema_version": "1.2.0",
  "rubric_version": "1.1",
  "license": "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
  "record": {
    "id": "O-0206",
    "slug": "future-of-life-institute",
    "title": "Future of Life Institute",
    "aliases": [
      "FLI"
    ],
    "status": "published",
    "last_reviewed": "2026-09-25",
    "review_interval_days": 90,
    "steward": null,
    "provenance": {
      "drafted_by": "ai",
      "reviewed_by": [
        "codex-review"
      ]
    },
    "risk_flags": [],
    "flags": [
      "provider-reported"
    ],
    "kind": "nonprofit",
    "homepage": "https://futureoflife.org/",
    "one_liner": "A nonprofit working on extreme risks from transformative technology; it built secure-hardware proofs of concept for AI governance and partners on a network-logger prototype.",
    "sources": [
      {
        "source": "S-3611",
        "supports": "self-description as independent nonprofit and mission to steer transformative technology away from extreme risks"
      },
      {
        "source": "S-1203",
        "supports": "Intel SGX proof of concept with Mithril Security: design aims and stated limits"
      },
      {
        "source": "S-3381",
        "supports": "AICert proof of concept with Mithril Security: TPM-based binding of weights to training inputs; stated limits"
      },
      {
        "source": "S-1511",
        "supports": "listed with SASH as building a confidential network logger prototype"
      },
      {
        "source": "S-1320",
        "supports": "named by SASH as an early partner"
      }
    ],
    "type": "organization",
    "url": "https://trustbutveri.fyi/organizations/future-of-life-institute/",
    "source_file": "content/organizations/future-of-life-institute.md",
    "flags_all": [
      "provider-reported"
    ],
    "body_markdown": "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:\n\n- 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 [[M-0008]].\n- 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]].\n- 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 [[I-0008]].",
    "body_text": "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.",
    "referenced_by": [
      {
        "id": "M-0008",
        "title": "TEE remote attestation for AI workloads",
        "url": "https://trustbutveri.fyi/mechanisms/tee-remote-attestation/"
      },
      {
        "id": "I-0008",
        "title": "SASH confidential network logger",
        "url": "https://trustbutveri.fyi/implementations/sash-confidential-network-logger/"
      },
      {
        "id": "O-0160",
        "title": "Singapore AI Safety Hub (SASH)",
        "url": "https://trustbutveri.fyi/organizations/singapore-ai-safety-hub/"
      },
      {
        "id": "S-3611",
        "title": "Future of Life Institute: Global Institutions Governing AI",
        "url": "https://trustbutveri.fyi/sources/fli-governing-ai-grant/"
      },
      {
        "id": "S-1203",
        "title": "Exploration of secure hardware solutions for safe AI deployment",
        "url": "https://trustbutveri.fyi/sources/fli-hardware-backed-compute-governance/"
      },
      {
        "id": "S-3381",
        "title": "Verifiable Training of AI Models",
        "url": "https://trustbutveri.fyi/sources/fli-verifiable-training-ai-models/"
      }
    ]
  }
}