Author

Luis Carranza

0 works0 citationsORCID

Recent research

  • AI & ComputingOpen access

    Oversubscribing One TEE: 512 Registered Tenants, a 1.22× Gain, and Isolation at 0.54 Percent

    One confidential GPU serves a limited number of concurrent tenants. This reportmeasures what happens when registration exceeds that number: idle tenants'key-separated KV state is parked to disk and revived on activation, on an AzureH100 confidential instance with SEV-SNP active a...

    Zenodo (CERN European Organization for Nuclear Research)2026-08-270 citationsDOI
  • AI & ComputingOpen access

    Oversubscribing One TEE: 512 Registered Tenants, a 1.22× Gain, and Isolation at 0.54 Percent

    One confidential GPU serves a limited number of concurrent tenants. This reportmeasures what happens when registration exceeds that number: idle tenants'key-separated KV state is parked to disk and revived on activation, on an AzureH100 confidential instance with SEV-SNP active a...

    Zenodo (CERN European Organization for Nuclear Research)2026-08-270 citationsDOI
  • AI & ComputingOpen access

    The Isometry Tax: At-Rest Leakage in Rotation-Isolated Multi-Tenant Vector Search as an Instance of Property-Preserving-Encryption Leakage, with Bounds on Its Mitigations

    Multi-tenant vector indexes promise large cost savings by sharing one approximate-nearestneighbour structure across many tenants. Per-tenant orthonormal rotation is an appealing way to isolate those tenants: each tenant's vectors are rotated under a per-tenant key, within-tenant...

    Zenodo (CERN European Organization for Nuclear Research)2026-08-264 citationsDOI
  • AI & ComputingOpen access

    Isolation Through Orthonormal Rotation Holds

    Per-tenant orthonormal rotation applied to attention K-vectors provides cryptographic isolation between tenants sharing a single language model instance. Within a tenant, rotation is an isometry — retrieval quality is preserved exactly. Across tenants, a wrong-key query returns c...

    Zenodo (CERN European Organization for Nuclear Research)2026-08-260 citationsDOI
  • AI & ComputingOpen access

    Isolation Through Orthonormal Rotation Holds

    Per-tenant orthonormal rotation applied to attention K-vectors provides cryptographic isolation between tenants sharing a single language model instance. Within a tenant, rotation is an isometry — retrieval quality is preserved exactly. Across tenants, a wrong-key query returns c...

    Zenodo (CERN European Organization for Nuclear Research)2026-08-264 citationsDOI