P069 Hardware enforcement of permitted use

Can chips be restricted to approved code, inference-only, or bounded training, and what throughput penalty does the best circumvention attack achieve?

Restricting chips to approved code, inference-only operation or bounded training, the cost of circumventing such restrictions, and the time to convert deployed compute to verified inference-only operation.

Status

Analyzed Designs only: RAND's licence-metered throttle (bounded training by operation budget, with a hardware cutoff sketch) and CNAS's on-chip restriction to approved code or models; Scher & Thiergart list inference-only chips and an operation disallow-list as building blocks and call them possibly 'extremely difficult or effectively impossible'. No prototype has refused a non-compliant job in a test (Harack et al. 2025). The circumvention clause has no work: no measured throughput penalty for the best attack, and RAND itself notes a clock-slowing throttle 'might be easy to circumvent with a cheap FIB edit'. Stated limit, not a failure: software-only mechanisms can verify use but not enforce it (Petrie & Aarne 2025).

When the counter for a functional unit (such as a floating-point multiplier block) exceeds the threshold set by the license, a multiplexer placed before the output of the functional unit can select an alternative output value of zero, ignoring the actual computation results.
Kulp et al. (2024), Hardware-Enabled Governance Mechanisms (RAND WR-A3056-1) (2024-01), L2186–2189

Posed by

Also raised in: Harack et al. (2025), Verification for International AI Governance (Oxford AIGI); Scher & Thiergart (2024), Mechanisms to Verify International Agreements About AI Development (MIRI); Petrie & Aarne (2025), Technical Options for Flexible Hardware-Enabled Guarantees (flexHEG Part 2); Aarne & Petrie (2025), International Security Applications of Flexible Hardware-Enabled Guarantees (flexHEG Part 3); Aarne, Fist & Withers (2024), Secure, Governable Chips (CNAS); Hausenloy & Li (2026), The Compute Verification Post; Kulp et al. (2024), Hardware-Enabled Governance Mechanisms (RAND WR-A3056-1); Wasil, Reed, Miller & Barnett (2024), Verification Methods for International AI Agreements; AI Security Forum, Requests for Discussion; Amodo (2026), AI 2040 Plan A — How You Can Help; Dean, Verification Plan (AI 2040); Proofworks, Living Verification Documents.

Sub-questions

IDSub-questionWhat the sources report
P069.1What training-throughput penalty does the best known attack achieve when training on inference-specialised chips, or on chips converted to inference-only via firmware/licences?open
P069.2Has any prototype refused to execute a training job deviating from a signed plan, in a red-team test?open
P069.3Can a firmware cluster-size cap (e.g. no training across more than 16 H100-equivalents) be bypassed by low-communication training or modified drivers while staying under the cap?open
P069.4What false-positive and false-negative rates does a chip-side 'unauthorised training' detector / flexHEG workload classifier achieve on a benchmark workload set against disguise?open
P069.5What throughput overhead does a firmware reporting mechanism impose on a representative training job?open
P069.6Can a single FIB edit remove a clock-throttle on a test chip, at what cost?open
P069.7How many weeks does it take to convert a stated share of global compute to verified inference-only?open
P069.8Can a 10^24 FLOP training run proceed on a cluster with scale-out interconnect removed (crude first-year modification)?open
P069.9Can hardware or software restrict chips to approved code/models or per-workload sign-off without algorithm access, given that software alone can verify but not enforce?a source suggests an answer (not checked)
P069.10Can a hardware license mechanism distinguish licensed from unlicensed inference, and give the licensor feedback on use (offline licensing is open-loop)?open

Sub-questions not yet stated precisely enough to check

IDSub-question
P069.11Can chips with hardcoded weights serve as on-device inference-only verification hardware?
P069.12Can an operation-stack disallow-list (e.g. blocking backpropagation) be enforced?
P069.13Which functionality should be throttled so dual-use workloads are hit while non-AI uses are spared, and can that line be drawn?
P069.14Has a commercial data centre of stated size run inference-only verification for a stated duration with third-party checking?
P069.15Can caps on technical inputs, vetoes on frontier-pushing runs, or enduring rulesets be implemented technically?

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 P069.5: What throughput overhead does a firmware reporting mechanism impose on a representative training job?

For P069.6: Can a single FIB edit remove a clock-throttle on a test chip, at what cost?

Data