Proposal Explorer

For the goal Prevent weight theft. Each of its claims is marked direct or supporting.

1. Communication between compute groups is bounded Supporting

Unaddressed

No mechanism in the proposal addresses it.

Goal claims not in the proposal

• Model weights have not left the facility Direct Add

Outside this map

• Insider and physical security. Nevo and colleagues group their 38 attack vectors into nine categories, which include unauthorised physical access, supply chain attacks and human intelligence. Access controls, insider threat programmes and physical security are outside this map's records. S. Nevo et al. 2024

No new hardware needed

Safeguard attestation

Published attempts to break a system, including those that found failures. Testing history does not show that open flaws are resolved.

• Safeguard attestation: Analysis

Claims not fully addressed

• Communication between compute groups is bounded No mechanism in the proposal addresses it.

Not linked to your claims

Safeguard attestation

Open significant flaws

5 flaws in 1 mechanism

• 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

  Theoretical argument · Significant · Open. 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}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R2 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 flaw 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

  Theoretical argument · Significant · Open. On the record

• 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}

  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.

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

  Related mechanism R1 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 flaw is mitigated. Add

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

• R2 Bandwidth limits and compartmentalization Add
  • Aimed at claim 1, Communication between compute groups is bounded, which is unaddressed.
• R1 Side-channel suppression for isolated facilities Add
  • Aimed at claim 1, Communication between compute groups is bounded, which is unaddressed.
• R2 On-chip telemetry from timing, memory and performance counters Add
  • Bears on the open significant flaw “Selective attestation leaves traffic uncovered” in Safeguard attestation. On-chip counters are a proposed route to evidence about everything a chip runs, including a second virtual machine that skips the safeguard.
• R1 Hardware-enabled guarantees (flexHEG) and guarantee processors Add
  • Bears on the open significant flaw “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.
• R3 Model identity attestation Add
  • Safeguard attestation waits on it. Safeguard evidence must be bound to the model actually served, which depends on model-identity attestation.
• R3 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

• R3 TEE remote attestation for AI workloads needed by Safeguard attestation Add
• R3 Model identity attestation needed by Safeguard attestation Add

Blockers

5 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 14}
  • 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 Model identity attestation ^{14 15}
  • 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}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Safeguard attestation.

Inputs and outputs

Depends on the design for Safeguard attestation.

Training data

Not involved: Safeguard attestation.

Safeguard attestation

None on the map

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. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
15. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original