Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Sampled inference recomputation

No new hardware needed

Safeguard attestation and Sampled inference recomputation

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
• Sampled inference recomputation, DiFR (Divergence From Reference): Analysis

Family findings

• Sampled inference recomputation

  Context for DiFR (Divergence From Reference). Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there.

  • Tolerance for numerical noise leaves a covert channel in Sampled inference recomputation

    Schemes that accept approximate matches can put an upper bound on an adversary's covert bandwidth, but they cannot close the channel. The weight-exfiltration detector cut exfiltratable information to under 0.5%, not to zero, on a 30-billion-parameter mixture-of-experts model under benign prompt traffic. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token. Across six models, that cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target the check that outputs match the declared model. ^{15 20 22}

    Known failure · Demonstrated attack · Significant · Open. On the record

    Related mechanism Operational use Deterministic and bit-exact inference: Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration. A pointer, not evidence that this failure is mitigated. Add

  • Only recorded traffic is checked in Sampled inference recomputation

    Recomputation checks that recorded, declared workloads are correct. It cannot show that the record is complete. The published schemes do not cover hidden workloads run on the same compute, or substituted work. Rinberg et al. say their exfiltration-detection scheme cannot stand alone. ^{15 23}

    Scope limitation · Theoretical argument. On the record

    Related mechanism Proposed Network taps and certifiers: Taps copy and hash all traffic on the monitored links, which bears on whether the traffic record is complete. They do not show what else ran on the same chips. A pointer, not evidence that this failure is mitigated. Add

  • Some inference optimizations are not covered in Sampled inference recomputation

    TOPLOC's authors state that it cannot detect speculative decoding in which a cheaper model does the decoding. They did not test whether it distinguishes types of key-value (KV) cache compression. DiFR was evaluated only on sampling from a single model. Its authors sketch an extension to one speculative-decoding algorithm but do not test it. ^{14 24}

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

  • Mixed hardware widens the honest baseline in Sampled inference recomputation

    When honest reference runs span different GPU types, the spread of benign scores grows. In DiFR's tests on Qwen3-30B-A3B, pooling A100 and H200 runs left Token-DiFR unable to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy separated them. Matched provider and verifier environments, or pooling that weights rare large deviations, restored detection. ¹⁴

    Known failure · Open question · Minor · Open. On the record

Open significant failures

3 failures in 2 mechanisms

• 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

• Statistical tolerance leaves a covert channel in DiFR (Divergence From Reference)

  Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration. ^{15 20 22}

  Known failure · Demonstrated attack · Significant · Open. On the record

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

Open questions

• Speculative decoding and multi-model sampling not evaluated in DiFR (Divergence From Reference)

  The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata. ¹⁴

  Open question · Open question. On the record

Open minor failures

1 mechanism with minor failures

• Mixed hardware widens the honest baseline in DiFR (Divergence From Reference)

  For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed to separate the two smallest tested changes, a temperature of 1.1 instead of 1.0 and a simulated top-2 sampling bug, at the target false-positive rate, while cross-entropy did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection. ¹⁴

  Known failure · Open question · Minor · Open. On the record

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

• Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors Add
  • 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.
• Operational use Hardware-attested weight binding Add
  • Safeguard attestation waits on it. Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.
• 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.

Missing prerequisites

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

Blockers

8 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 25}
  • 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 ^{25 26}
  • 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}
• Sampled inference recomputation
  • The verifier needs the model weights, so outsiders cannot use the method to verify providers of closed-weights models. Privacy & leakage ¹⁴
  • The verifier must know and match the provider's sampling procedure, and in one prototype a sampling mismatch in a newer vLLM version produced large spurious logit differences. Performance & compatibility ^{14 17}
  • No independent red-team of DiFR's consistency check has been published, Amodo rates recomputation red-teaming 'not started', and the one independent attack study targets an exfiltration detector built on the same statistic. Adversarial validation ^{19 20}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Safeguard attestation.

Unspecified for Sampled inference recomputation. Check the implementation record.

Inputs and outputs

Depends on the design for Safeguard attestation.

Unspecified for Sampled inference recomputation. Check the implementation record.

Training data

Not involved: Safeguard attestation.

Unspecified for Sampled inference recomputation. Check the implementation record.

Safeguard attestation

None on the map

Sampled inference recomputation

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• Research demo DiFR (Divergence From Reference) Research prototype
• Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• Proposed SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)
• Operational use TOPLOC Open-source project, Prime Intellect

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. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
15. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
16. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
17. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
18. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
19. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
20. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
21. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
22. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
23. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
24. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
25. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
26. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original