Skip to content
Apart Research
Apart Research
Contact us
Sprint projectFeb 2, 2026London

Risks and Benefits of Emerging Cryptographic Primitives for Compute Governance

Harry Powell · Team Obfuscurity

Submitted to The Technical AI Governance Challenge. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Risks and Benefits of Emerging Cryptographic Primitives for Compute Governance

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

International cooperation on AI safety requires verification without surveillance. We examine how emerging cryptographic primitives - Fully Homomorphic Encryption (FHE) and Indistinguishability Obfuscation (iO) - could enable privacy-preserving compute governance.

We present two protocols of increasing strength. The first uses FHE to allow compute providers to enforce safety policies on encrypted programs, preserving user privacy while requiring hardware verification for provider compliance. The second adds obfuscation to provide cryptographic guarantees against user-provider collusion, reducing hardware verification to boundary monitoring.

Neither protocol requires users to disclose their programs in plaintext. Both point toward a future where cryptography and physical verification work together to govern powerful computation.

To validate this capability, we include a reference implementation of the second protocol’s architecture. This proof-of-concept utilizes Zero-Knowledge proofs (Schnorr) and ElGamal encryption to demonstrate that boundary verification can be enforced cryptographically without ever decrypting the user's workload.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. Impact potential & innovation: 3

    I appreciate the honesty here in describing the two-protocol structure. But the safety checker section is vague, and overall the project is very conceptual.

    Execution quality: 2

    There is not a huge amount of execution here. The implementation is fine but insubstantial. And the LLM-based safety checker seems weak.

    Presentation & clarity: 4

    Well-structured, honest about limitations. I particularly like the comparison table - it's clear & useful.

  2. Impressive and well thought out project!The two protocol design with escalating trust assumptions is clean and the threat model analysis is honest. Next steps would be going deeper into what "safety checking" means for realistic training workloads in the wild

Cite this project

@misc{powell2026risks,
  title = {{Risks and Benefits of Emerging Cryptographic Primitives for Compute Governance}},
  author = {Harry Powell},
  year = {2026},
  month = feb,
  note = {Submitted to The Technical AI Governance Challenge, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/risks-and-benefits-of-emerging-cryptographic-primitives-for-compute-governance-4w1w}},
  url = {https://apartresearch.com/sprints/projects/risks-and-benefits-of-emerging-cryptographic-primitives-for-compute-governance-4w1w}
}

More from The Technical AI Governance Challenge

All 47 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026