P013 Designer backdoors and hidden functionality
Can a verifier gain assurance that a chip design is free of designer-inserted backdoors or hidden execution paths, at a stated detection rate on seeded trojans?
Detecting designer backdoors and hidden functionality.
Status
Analyzed Design options only, for the guarantee processor: open-sourcing the design and logic for third-party analysis against physical scans of randomly selected chips, executing guarantee logic on publicly auditable FPGAs, and running redundant guarantee processors from different manufacturers in lock-step; flexHEG Part 3 adds collaborative design with justification of every choice. Nothing built, no outside review of real silicon, and no detection rate on seeded trojans anywhere in the held sources; the binning clause (dormant functionality) has only RAND's design rule that there be none.
To increase trust that backdoors have not been added to the Guarantee Processor design or manufacturing process, some options are: … Open-sourcing the guarantee processor design and guarantee logic, which could then be analyzed and compared with physical scans of randomly selected chips.
Posed by
- Harack et al. (2025), Verification for International AI Governance (Oxford AIGI):
proving that the mechanisms are not being used for other covert purposes may be extremely difficult
(Exec. summary, p.11, L582–583) (source states the problem but not the quantity the question asks for)
Also raised in: 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); 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); Ilhan, Withers, Gietz & Harack (2026), Verifiable Semiconductor Manufacturing (Oxford AIGI); Cankaya (2026), A System Overview for Near-Term, Low-Trust AI Compute Verification (v0.2); Kulp et al. (2024), Hardware-Enabled Governance Mechanisms (RAND WR-A3056-1); AI Security Forum, Requests for Discussion; Amodo (2026), AI 2040 Plan A — How You Can Help; Proofworks, Living Verification Documents.
Sub-questions
| ID | Sub-question | What the sources report |
|---|---|---|
| P013.1 | Has an outside reviewer confirmed, on real silicon, that an on-chip governance block / guarantee processor has no undeclared function (e.g. no key-leak backdoor), via joint audit or random inspection? | open |
| P013.2 | Can an integrator test a black-box third-party IP core for hidden functionality with a stated detection rate on seeded trojans? | open |
| P013.3 | Can dormant functionality left by binning be found by layout inspection or re-enabled by chip edits, and what does a separate mask set cost instead? | implied by a source, not stated as open |
Sub-questions not yet stated precisely enough to check
| ID | Sub-question |
|---|---|
| P013.4 | Is there a protocol that gives a Verifier assurance against a backdoor inserted by the chip designer, i.e. that a design is free of secret execution paths? |
| P013.5 | Can states or vendors participating in joint/open/multi-vendor design plant subtle vulnerabilities, making the governance hardware itself a sabotage vector? |
| P013.6 | Have true hardware trojans been observed in the wild? |
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 P013.1: Has an outside reviewer confirmed, on real silicon, that an on-chip governance block / guarantee processor has no undeclared function (e.g. no key-leak backdoor), via joint audit or random inspection?
For P013.2: Can an integrator test a black-box third-party IP core for hidden functionality with a stated detection rate on seeded trojans?
For P013.3: Can dormant functionality left by binning be found by layout inspection or re-enabled by chip edits, and what does a separate mask set cost instead?
Data
- problems.csv — one row per problem
- problem_status.csv — status, scope and evidence per problem
- problem_sources.csv — the posed-by quote and other documents per problem
- leaves.csv — all sub-questions, including those without a checkable form
- leaf_sources.csv — every source row behind each sub-question