Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Tamper evidence for verifier devices

No new hardware needed

Safeguard attestation

Not counted

Excluded by your filters: Hardware-enabled guarantees (flexHEG) and guarantee processors

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

• Safeguard attestation: Analysis
• Hardware-enabled guarantees (flexHEG) and guarantee processors: Analysis · excluded by filters
• Tamper evidence for verifier devices: Analysis

Excluded by your filters

• Hardware-enabled guarantees (flexHEG) and guarantee processors Needs changes to future chip designs; the filter allows existing chips only.

Open significant flaws

14 flaws in 3 mechanisms

• 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. In the proposal.

• State attackers can likely defeat current secure enclosures in Hardware-enabled guarantees (flexHEG) and guarantee processors

  The flexHEG authors write that "nation-state attackers can likely compromise the best current secure enclosures", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures "would not be insurmountable for a determined and well-resourced adversary", although they raise costs and can reveal tampering. ^{15 17}

  Theoretical argument · Significant · Open. On the record

• Firmware-only retrofits rely on Secure Boot, which fault injection can bypass in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers. ¹⁵

  Theoretical argument · Significant · Open. On the record

• Many important rules cannot be checked on-chip in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Malicious intent "is not a technical property observable on-chip", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset "may not be entirely feasible" for the same reason. ^{14 16}

  Theoretical argument · Significant · Open. On the record

• FLOP accounting can be laundered through external data in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Results of earlier or parallel workloads could be hidden in the "external data" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed. ¹⁵

  Theoretical argument · Significant · Open. On the record

• Supply-chain diversion and hidden backdoors in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices. ^{15 16}

  Open question · Significant · Open. On the record

  Related mechanism R1 Chip registries and manufacturing records: Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors. A pointer, not evidence that this flaw is mitigated. Add

• Coverage stops at flexHEG-equipped chips in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be "practically quite difficult". ^{14 16}

  Open question · Significant · Open. On the record

  Related mechanism R1 Chip registries and manufacturing records: Accounts for which chips exist and who holds them. A pointer, not evidence that this flaw is mitigated. Add

  Related mechanism R1 Remote detection of data centres: Looks for undeclared facilities that hold other chips. A pointer, not evidence that this flaw is mitigated. Add

• Seals are often defeated with simple methods in Tamper evidence for verifier devices

  Published defeats of general security seals. They warn about proposed verifier-device seals, but do not demonstrate defeat of an AI verification enclosure or sensor.

  In 1996 a Los Alamos vulnerability assessment defeated all 94 security seals it examined, with 132 defeats in total, using rapid, inexpensive, low-tech methods. It found that seal cost did not predict security. In 2001 Johnston reported that high-tech seals are often easier to defeat than low-tech ones. ^{26 27}

  Demonstrated attack · Significant · Open · Mechanism-class evidence. On the record

• Security depends on inspection protocols in Tamper evidence for verifier devices

  An inspection and protocol requirement drawn from safeguards and enclosure studies, not a reported break of a deployed AI verifier.

  Johnston argues that a seal is no better than the protocols for using it, and that inspectors are usually given little useful information on how to detect tampering. The Sandia survey notes that larger enclosures are hard to inspect fully and that sensor data must be authenticated. ^{25 27}

  Theoretical argument · Significant · Open · Mechanism-class evidence. On the record

• Attack classes outside published models in Tamper evidence for verifier devices

  The radio compensation result is emulated using measured channel data under a known-reference attacker model. It is not a physical bypass demonstration against an AI verifier enclosure.

  The authors of the batteryless cover say they cannot assess chemical-solvent attacks, which exceed their expertise, and deem cover removal impractical. Anti-Tamper Radio's reference can drift as the environment or measurement system ages; the authors suggest gradually renewing the reference. A 2025 follow-up by some of the same authors shows, by emulation on measured channel data, that an attacker who knows the reference channel and the needle's effect on it could inject a signal that cancels the change caused by a needle insertion. It proposes a reconfigurable intelligent surface that randomizes the channel as a countermeasure. ^{20 21 28}

  Open question · Significant · Open · Mechanism-class evidence. On the record

Not yet demonstrated

R1 Hardware-enabled guarantees (flexHEG) and guarantee processors

Need new chip designs

Hardware-enabled guarantees (flexHEG) and guarantee processors

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

• 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 Chip registries and manufacturing records Add
  • Bears on the open significant flaw “Supply-chain diversion and hidden backdoors” in Hardware-enabled guarantees (flexHEG) and guarantee processors. Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors.
  • Bears on the open significant flaw “Coverage stops at flexHEG-equipped chips” in Hardware-enabled guarantees (flexHEG) and guarantee processors. Accounts for which chips exist and who holds them.
  • Hardware-enabled guarantees (flexHEG) and guarantee processors waits on it. Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities.
• R1 Remote detection of data centres Add
  • Bears on the open significant flaw “Coverage stops at flexHEG-equipped chips” in Hardware-enabled guarantees (flexHEG) and guarantee processors. Looks for undeclared facilities that hold other chips.
• 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.
  • Hardware-enabled guarantees (flexHEG) and guarantee processors depends on it.

Missing prerequisites

• R3 TEE remote attestation for AI workloads needed by Safeguard attestation and Hardware-enabled guarantees (flexHEG) and guarantee processors Add
• R3 Model identity attestation needed by Safeguard attestation Add
• R1 Chip registries and manufacturing records needed by Hardware-enabled guarantees (flexHEG) and guarantee processors Add

Shared foundations

• TEE remote attestation for AI workloads relied on by Safeguard attestation and Hardware-enabled guarantees (flexHEG) and guarantee processors

Blockers

14 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 29}
  • 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 ^{29 30}
  • 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}
• Hardware-enabled guarantees (flexHEG) and guarantee processors
  • Integrated flexHEG needs substantial help from the accelerator manufacturer, and the authors estimate 3.7–7.9 years, from when the manufacturer starts work, for such hardware to displace other accelerators in frontier development. Access & governance ¹⁵
  • State-level attackers who hold the hardware can likely compromise the best current secure enclosures. Hardware trust. Waits on Tamper evidence for verifier devices ^{15 17}
  • Rival states would need to trust the design and manufacture of guarantee processors and enclosures, for example through open design, redundant processors from each side or oversight of production. Hardware trust ^{14 16}
  • Restricting future rule updates would need a formal language for rules, which the authors judge most likely infeasible for early flexHEG versions. Protocol soundness ¹⁴
  • Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities. Coverage & hidden compute. Waits on Chip registries and manufacturing records ¹⁶
• Tamper evidence for verifier devices
  • No tamper-evident enclosure has been designed for AI verifier hardware at retrofit scale. Hardware trust ¹³
  • Battery-backed designs add bulk, limit operating temperature (+10 °C to +35 °C for the IBM 4765) and complicate transport. Performance & compatibility ²¹
  • Active monitoring needs power, and visual inspection of large enclosures faces access limits. Access & governance ²⁵
  • No evaluation has been published in the AI verification setting. Adversarial validation ¹³

From the family or selected implementation's record. ?

Model weights

Depends on the design for Safeguard attestation.

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Tamper evidence for verifier devices.

Inputs and outputs

Depends on the design for Safeguard attestation.

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Tamper evidence for verifier devices.

Training data

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Safeguard attestation and Tamper evidence for verifier devices.

Safeguard attestation

None on the map

Hardware-enabled guarantees (flexHEG) and guarantee processors

None on the map

Tamper evidence for verifier devices

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project

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. Flexible Hardware-Enabled Guarantees for AI Compute, J. Petrie et al. (2025). Original
15. Technical Options for Flexible Hardware-Enabled Guarantees, J. Petrie & O. Aarne (2025). Original
16. International Security Applications of Flexible Hardware-Enabled Guarantees, O. Aarne & J. Petrie (2025). Original
17. Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090, G. Kulp et al. (2024). Original
18. Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing, O. Aarne et al. (2024). Original
19. Hardware-Enabled Mechanisms for Verifying Responsible AI Development, A. O'Gara et al. (2025). Original
20. Anti-Tamper Radio: System-Level Tamper Detection for Computing Systems, P. Staat et al. (2022). Original
21. Secure Physical Enclosures from Covers with Tamper-Resistance, V. Immler et al. (2019). Original
22. ImpedanceVerif: On-Chip Impedance Sensing for System-Level Tampering Detection, T. Mosavirik et al. (2023). Original
23. IBM 4765 Cryptographic Coprocessor Security Module: Security Policy, IBM Corporation (2012). Original
24. PHYSEC SEAL: Change detection for maximum safety, PHYSEC GmbH (2026). Original
25. Tamper-Indicating Enclosures, A Current Survey, H. A. Smartt & Z. N. Gastelum (2015). Original
26. Physical Security and Tamper-Indicating Devices, R. G. Johnston & A. R. E. Garcia (1996). Original
27. Tamper Detection for Safeguards and Treaty Monitoring: Fantasies, Realities, and Potentials, R. G. Johnston (2001). Original
28. Anti-Tamper Radio Meets Reconfigurable Intelligent Surface for System-Level Tamper Detection, M. S. Tabar et al. (2025). Original
29. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
30. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original