Proposal Explorer

Add claims to see which ones the mechanisms address.

Operational use

• Operational use Hardware-attested weight binding for hardware-attested weight binding showing users that a service runs its committed weights

Built for an adversarial prover

Remote detection of data centres

No new hardware needed

Safeguard attestation, Remote detection of data centres and Hardware-attested weight binding

Failures since mitigated

• Launch-state attestation does not by itself cover weights loaded later in Hardware-attested weight binding ^{9 19}

Attack testing records published testing for this use. It does not by itself show independent review, a formal proof or that a deployed system is secure.

• Safeguard attestation: Analysis
• Remote detection of data centres: Analysis
• Hardware-attested weight binding: Independent red-team

Open critical failures

• Underlying attestation can be forged or relayed in Hardware-attested weight binding

  Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.

  The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol. ^{4 7 10 11 12 20}

  Response: The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.

  Known failure · Demonstrated attack · Critical · Open · Inherited finding. On the record · Related finding in TEE remote attestation for AI workloads

  Related mechanism Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors: A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically. A pointer, not evidence that this failure is mitigated. Add

Open significant failures

2 failures in 1 mechanism

• Components outside the attested boundary in Safeguard attestation

  In the proof-of-guardrail experiments, the guardrail model and the agent's backend model were both reached through external APIs, and the authors leave the decision to trust those APIs to the verifier. The measured wrapper must also have no vulnerability that lets the unmeasured agent bypass the guardrail, for example by executing arbitrary commands inside the enclave. The code's README states that the enclave does not currently restrict the agent's arbitrary command execution, which could be used to bypass guardrails. ^{1 2}

  Known failure · Theoretical argument · Significant · Open. On the record

• Memory-bus interposition extracts attestation keys and forges attestations in Safeguard attestation

  Applies to variants using the affected Intel or AMD trust roots. PAL*M excludes physical attacks. A TDX-backed safeguard claim against a physical host attacker would be defeated, but these studies do not demonstrate a break of the AWS Nitro proof-of-guardrail prototype or of verifier-side recomputation.

  The TEE findings cover DDR5 attacks on Intel TDX, the H100 relay demonstration, DDR4 attacks on AMD SEV-SNP, and software-only SEV-SNP forgery before AMD's fixes. These are inherited hardware limits; a governance analysis explains why physical access matters in a treaty setting. ^{1 4 7 8 9 10 11 12 13}

  Response: Intel and AMD place the physical attack class outside their threat models, according to the researchers. AMD reports firmware fixes for RMPocalypse.

  Known failure · Demonstrated attack · Significant · Open · Inherited finding. On the record · Related finding in TEE remote attestation for AI workloads

  Related mechanism Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors: A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically. A pointer, not evidence that this failure is mitigated. Add

Scope limitations

• Attestation shows a safeguard ran, not that it is effective in Safeguard attestation

  Proof of guardrail ensures that the guardrail executed, but the guardrail can still err or be jailbroken. Because the guardrail must be open source, a malicious developer can attack it with jailbreaks while still presenting a valid proof. In the authors' evaluation, Llama Guard 3 reached an F1 score of 0.56 on the unsafe class of the ToxicChat dataset. The authors state that proof of guardrail should not be interpreted or advertised as proof of safety. ¹

  Scope limitation · Theoretical argument. On the record

• Selective attestation leaves traffic uncovered in Safeguard attestation

  Attestations are issued per response. In the prototype, the agent offers them when it receives high-stakes questions, so nothing shows that unattested traffic went through the same path. PAL*M's authors note that a prover could cherry-pick favourable executions, and suggest verifier-published nonces or requesting only session-level proofs. A governance analysis notes that auditors also need assurance that all activity is accounted for, since a host could start a second confidential virtual machine that bypasses monitoring. ^{1 4 9}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Research demo On-chip telemetry from timing, memory and performance counters: On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard. A pointer, not evidence that this failure is mitigated. Add

• Measurements may omit behaviour-relevant configuration or runtime changes in Safeguard attestation

  Every component that influences inference behaviour must be covered by the launch measurement, including feature flags, environment variables and invocation arguments. A launch measurement also does not show that a program keeps running as measured if the kernel is later compromised. ⁹

  Scope limitation · Theoretical argument. On the record

• Facilities can be disguised or hidden in Remote detection of data centres

  Halstead and Larsen discuss two ways to hide a facility. One is to disguise it as a legitimate industrial site. The other is to build it underground, with cooling that avoids visible heat plumes. They note that the underground option requires bespoke engineering. ¹⁴

  Scope limitation · Theoretical argument. On the record

• Small sites may not be detectable in Remote detection of data centres

  Halstead and Larsen conclude that a sufficiently small covert project could not be ruled out with confidence. In their estimates, the chance of detection is lower for smaller sites. Krawec notes that small data centres in existing buildings may lack the distinctive features of large facilities. ^{14 16}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Chip registries and manufacturing records: Accounts for chips from the fab onwards, which does not depend on a site being visible. A pointer, not evidence that this failure is mitigated. Add

• For private models, a user can confirm consistency but not content in Hardware-attested weight binding

  When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy. ^{19 24}

  Scope limitation · Open question. On the record

Open questions

• Search for unknown sites is undemonstrated in Remote detection of data centres

  Krawec reports that telling data centres apart from other industrial facilities systematically is difficult. Automating detection would need large amounts of training imagery and a purpose-trained model. In Krawec's words, automated data-centre detection "remains primarily conceptual at present". ¹⁶

  Open question · Open question. On the record

Not yet demonstrated

Proposed Remote detection of data centres

Mechanisms on the map that are not in the proposal. Pointers, not recommendations. ?

• Operational use TEE remote attestation for AI workloads Add
  • Safeguard attestation waits on it. Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference.
  • Safeguard attestation waits on it. Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack.
  • Hardware-attested weight binding waits on it. Attestation that resists physical attackers, for the enclave variant.
• Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors Add

  Excluded by filters: needs new chips

  • Bears on the open critical failure “Underlying attestation can be forged or relayed” in Hardware-attested weight binding. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
  • Bears on the open significant failure “Memory-bus interposition extracts attestation keys and forges attestations” in Safeguard attestation. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.

Missing prerequisites

• Operational use TEE remote attestation for AI workloads needed by Safeguard attestation and Hardware-attested weight binding Add

Shared foundations

• TEE remote attestation for AI workloads relied on by Safeguard attestation and Hardware-attested weight binding

Blockers

9 blockers recorded

• Safeguard attestation
  • No published design shows that all of a provider's traffic passes through the attested safeguard path; current evidence covers individual attested responses. Coverage & hidden compute ^{1 9}
  • Frontier model inference typically needs several GPUs, GPU confidential computing is less mature than CPU support, and CPU inference, which an enclave prototype had to use, ran about 100 times slower than GPU inference. Performance & compatibility. Waits on TEE remote attestation for AI workloads ^{9 24}
  • Trust rests on a small number of hardware vendors, and a per-CPU Intel attestation key has been extracted by physical attack. Hardware trust. Waits on TEE remote attestation for AI workloads ^{7 9}
  • Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation. Evidence binding. Waits on Hardware-attested weight binding ^{19 24}
  • No independent red-team or audit of a safeguard-attestation system has been published, and the available prototypes are described by their authors as proofs of concept that have not been stress-tested by a counterparty. Adversarial validation ^{2 6}
• Remote detection of data centres
  • Wide-area, automated detection of data centres is not yet practical and needs large training datasets. Coverage & hidden compute ¹⁶
  • No measured detection or false-alarm rates for finding undeclared facilities have been published. Adversarial validation ^{14 16}
  • Recent high-resolution imagery is costly, is limited by weather and needs trained analysts. Access & governance ¹⁶
• Hardware-attested weight binding
  • Attestation that resists physical attackers, for the enclave variant. Hardware trust. Waits on TEE remote attestation for AI workloads ⁷

From the family or selected implementation's record. ?

Model weights

Depends on the design for Safeguard attestation.

Hidden by Hardware-attested weight binding.

Not involved: Remote detection of data centres.

Inputs and outputs

Depends on the design for Safeguard attestation.

Not involved: Remote detection of data centres.

Unspecified for Hardware-attested weight binding. Check the implementation record.

Training data

Not involved: Safeguard attestation, Remote detection of data centres and Hardware-attested weight binding.

Safeguard attestation

None on the map

Remote detection of data centres

None on the map

Hardware-attested weight binding

• Research demo Attestable Audits Research prototype, University of Cambridge
• Research demo PAL*M Research prototype, University of Waterloo
• Operational use Tinfoil model identity (Modelwrap) Product, Tinfoil

1. Proof-of-Guardrail in AI Agents and What (Not) to Trust from It, X. Jin et al. (2026). Original
2. Verifiable-ClawGuard: proof-of-guardrail reference code, SaharaLabsAI (2026). Original
3. Safety Without Compromising on Privacy, D. McCann-Sayles et al. (2026). Original
4. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). Original
5. Enabling Verifiably-Scoped Monitoring through Large Language Models and Trusted Compute, B. Penchas et al. (2026). Original
6. Auditor-in-a-Box: Tools for Third-Party Auditing, R. Rinberg & B. Penchas (2026). Original
7. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). Original
8. DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 Writes, J. De Meulemeester et al. (2026). Original
9. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). Original
10. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). Original
11. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). Original
12. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). Original
13. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
14. Covert AI Projects, B. Halstead & T. Larsen (2026). Original
15. Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment, M. Baker et al. (2025). Original
16. Tracking Hyperscale AI Data Center Growth with Satellite Imagery, C. Krawec (2026). Original
17. Introducing the Frontier Data Centers Hub, Epoch AI (2025). Original
18. AI Data Centers Documentation – Methodology, Epoch AI (2026). Original
19. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original
20. A primer on secure enclaves, Tinfoil (2026). Original
21. Backend infrastructure, Tinfoil (2026). Original
22. How verification works in Tinfoil, Tinfoil (2026). Original
23. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). Original
24. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original