P059 GPU confidential computing and link encryption: availability and overhead

Which shipping accelerators support multi-GPU confidential computing and encrypted links, at what throughput cost and with what key handling?

Which accelerators ship multi-GPU confidential computing / encrypted NVLink and links, at what throughput cost, with what binding and key handling.

Terms: confidential computing: keeping data encrypted even while a chip is processing it. NVLink: Nvidia's high-speed link between GPUs. AES-GCM: a standard method for encrypting and authenticating data in transit.

Status

Started Measured on one Huawei Ascend 910A accelerator, a vendor research prototype of firmware-only confidential computing: 0.028-0.91% added inference latency. Single device and inference only; no multi-device or training overhead has been published. A workshop participant reports an unpublished characterisation of training overhead from 2 to 1,024 GPUs; it is not counted, since no numbers are public. Availability: in January 2026 only the H100 offered working confidential computing; cluster-scale confidential computing on Blackwell at near-unencrypted speed is a vendor claim. Link encryption: roughly 3% of compute to encrypt NVLink traffic is a desk estimate.

introduces minimal performance loss during the inference pass(0.91% in GPT2-neo125M and 0.028% in Llama3-Chat-QA-1.5-8B model
Dhar et al. (2024), Ascend-CC: Confidential Computing on Heterogeneous NPU for Emerging Generative AI Workloads (Huawei) (2024), L140

Posed by

Also raised in: Reuel, Bucknall et al. (2025), Open Problems in Technical AI Governance, compute sections; Harack et al. (2025), Verification for International AI Governance (Oxford AIGI); Baker, Kulp, Marks, Brundage & Heim (2025), Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment (RAND WR-A4077-1); Petrie, Aarne, Ammann & Dalrymple (2025), Overview of Flexible Hardware-Enabled Guarantees (flexHEG Part 1); Petrie & Aarne (2025), Technical Options for Flexible Hardware-Enabled Guarantees (flexHEG Part 2); Ansari (2026), Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification; Harack (2026), AI Verification: Infrastructure for Prosperity, Governance, and Peace (Lawfare); AI Security Forum, Requests for Discussion; Proofworks, Living Verification Documents.

Sub-questions

IDSub-questionWhat the sources report
P059.1What throughput overhead does confidential computing impose on Hopper vs Blackwell for a fixed training and a fixed inference workload?open
P059.2Which shipping accelerators (H100, B200, MI300X, TPU, Trainium, Ascend) support GPU CC today, and what fraction of installed data-centre FLOP/s does that cover?a source suggests an answer (not checked)
P059.3Can a GPU attestation report be bound to a unique registry-checkable device identity and to a hash of the input data, surviving independent review?open
P059.4Can current accelerators emit signed commitments to (code, input, output) hashes per job at line rate, with audited firmware and stated overhead?open
P059.5Can an SM2/TCM-rooted Ascend attestation be translated into a DICE/SPDM-verifiable report by a neutral gateway?open
P059.6At what sampling rate and aggregation does leakage from GPU power telemetry under CC fall below a stated leakage rate?a source suggests an answer (not checked)
P059.7Is there a formally verified or audited hypervisor that hosts GPU AI workloads, at what overhead?partly answered
P059.8Can PCIe/DMA reads of HBM by a third-party device be spoofed, and how far can a verifier trust them when CC blocks third-party DMA?open
P059.9What is the measured overhead (% compute/power) and added latency (ns) of inline AES-GCM at NVLink-class rates (~900 GB/s)?partly answered
P059.10Does InfiniBand support line-rate link encryption for inter-enclave traffic on current hardware?a source suggests an answer (not checked)
P059.11For randomized authentication that samples a stated fraction of blocks, with a stated number of blocks modified, what is the detection probability, confirmed empirically?partly answered
P059.12What throughput overhead does attested/confidential execution impose for multi-node training at a stated cluster scale (measured, not simulated), and is it production-available?partly answered
P059.13What serving-throughput overhead does GPU confidential computing with per-response attestation impose in production?open

Sub-questions not yet stated precisely enough to check

IDSub-question
P059.14How is AES-GCM nonce reuse prevented across a large cluster?
P059.15How is spoofing contained when one node holding source keys is compromised (and dropped packets handled)?
P059.16Can randomized authentication hide which packets are authenticated from side channels (always-on crypto, canary probing)?
P059.17Can devices keep verifiable logs of what results (e.g. weights) they sent to which other devices?
P059.18How is integrity of the whole hardware/firmware/framework stack (e.g. PyTorch) ensured for cryptographic audit trails?

Possibly relevant work found by automated search

Found by AI agents searching for this problem's sub-questions, mostly by keyword and citation in the OpenAlex scholarly database and on the web; a second AI pass reviewed each one, and we spot-checked some by hand. They seemed reasonably related, as far as one can tell from outside each paper's field. Some come from neighbouring fields, such as arms control and financial audit, and bear on the problem by analogy. Not reviewed against the status above; a paper listed here does not change that status. 928 of 1052 quotes checked word for word against the paper's text.

For P059.1: What throughput overhead does confidential computing impose on Hopper vs Blackwell for a fixed training and a fixed inference workload?

For P059.3: Can a GPU attestation report be bound to a unique registry-checkable device identity and to a hash of the input data, surviving independent review?

For P059.5: Can an SM2/TCM-rooted Ascend attestation be translated into a DICE/SPDM-verifiable report by a neutral gateway?

For P059.9: What is the measured overhead (% compute/power) and added latency (ns) of inline AES-GCM at NVLink-class rates (~900 GB/s)?

Data