The declared evaluation was run

On this page

Mechanisms

R2 Confidential multi-party verificationprimary
Attestable Audits binds the model, audit code and data, and result. PySyft's pilot ran an agreed private evaluation with participant-accepted opaque-code and cloud trust assumptions ⁴ ⁹.
R3 TEE remote attestation for AI workloads ⚠supporting
Measures the enclave software and supplies the hardware root for evaluation attestations. Attestable Audits additionally binds model, audit and result ⁸; enclave launch attestation alone does not establish the full evaluation claim.

R2 Attestable Auditsprimary
Assessed use: showing users that the model answering them is the audited oneThe audit protocol binds the model hash, audit code and data, and result in a published attestation ¹.
R2 Coveprimary
Assessed use: composing owner-approved confidential workflow stages on Intel TDXReviewed workflow manifests and attested certificates bind evaluation stages to admitted inputs, results and predecessor evidence, under the documented host and review assumptions ¹.
R2 PAL*Mprimary
Assessed use: attesting declared model operations on a confidential CPU–GPU prototypeEvaluation attestations bind the operation, model, tokenizer, test dataset and reported metric ¹.
R2 PySyft double-blind evaluationsprimary
Assessed use: evaluating a private model on private prompts, neither party seeing the other's inputsBoth parties approve an attested evaluation on their submitted assets. The pilot accepted proprietary model code that could not all be inspected or allowlisted; it does not establish ongoing serving identity ¹.