Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Bounding unexplained information in outputs

No new hardware needed

Safeguard attestation and On-chip telemetry from timing, memory and performance counters

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
• Bounding unexplained information in outputs: Independent red-team
• On-chip telemetry from timing, memory and performance counters: Red-teamed

Open significant failures

5 failures in 3 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

• Prompt-controlled entropy inflation widens the covert channel in Bounding unexplained information in outputs

  Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic. ^{15 16}

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

  Related mechanism Operational use Deterministic and bit-exact inference: Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata. A pointer, not evidence that this failure is mitigated. Add

• Adversarially disguised fine-tuning partly evades classification in On-chip telemetry from timing, memory and performance counters

  Across 20 evasion strategy families in five monitor-evader rounds, the classifier's accuracy against the most challenging disguised workloads held out from training was 43–87%. White-box LoRA fine-tuning was the only evasion family detected less than half the time. The evaluation covered single nodes, PyTorch-level evasion and NVIDIA hardware. ²⁰

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

• Counters leak information about protected workloads in On-chip telemetry from timing, memory and performance counters

  Performance counters have been used as a side channel against TEEs, for example in CounterSEVeillance. NVIDIA disables performance counters in full confidential-computing mode, stating that they could provide an avenue for side-channel attacks. Richer counters for verification therefore pull against confidentiality. ^{9 21}

  Known failure · Theoretical argument · 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. In the proposal.

• 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

• Information the declared computation explains is not bounded in Bounding unexplained information in outputs

  The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows. ^{14 17}

  Scope limitation · Theoretical argument. On the record

• Channels other than checked outputs are outside the bound in Bounding unexplained information in outputs

  The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result. ^{13 15}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Side-channel suppression for isolated facilities: Physical side channels need separate suppression, which is this mechanism's purpose. A pointer, not evidence that this failure is mitigated. Add

• Software-read telemetry can be forged by the operator in On-chip telemetry from timing, memory and performance counters

  NVML-based classification assumes trustworthy telemetry. Without a tamper-resistant read path, an authenticated telemetry channel and secure boot of the monitoring software, an operator who controls the full software stack could forge counter values. Monfared et al. start from the same premise: current GPUs expose little trusted telemetry and can be modified or virtualized. ^{18 20}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors: A guarantee processor on the chip would give the tamper-resistant, authenticated telemetry path the flaw says is missing. A pointer, not evidence that this failure is mitigated. Add

• Timing challenges do not identify the individual chip in On-chip telemetry from timing, memory and performance counters

  GEMM and VDF challenges can be answered by identical GPUs elsewhere, and floating-point fingerprints distinguish GPU models, not individual devices. GPU virtualization adds timing leakage that prevents attributing compute use. ¹⁸

  Scope limitation · Theoretical argument. On the record

Open questions

• The facility-level design is untested in Bounding unexplained information in outputs

  The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published. ¹⁴

  Open question · Open question. On the record

• No quantified error rates or formal thresholds for timing primitives in On-chip telemetry from timing, memory and performance counters

  Monfared et al. state that false-positive and false-negative rates are not quantified and leave hardware-specific formal thresholds to future work. ¹⁸

  Open question · Open question. On the record

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

• Operational use Deterministic and bit-exact inference Add
  • Bears on the open significant failure “Prompt-controlled entropy inflation widens the covert channel” in Bounding unexplained information in outputs. Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata.
  • Bounding unexplained information in outputs waits on it. Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.
• 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.
  • On-chip telemetry from timing, memory and performance counters waits on it. Shipping accelerators need a tamper-resistant, authenticated telemetry path.
• 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.
  • On-chip telemetry from timing, memory and performance counters depends on it.
• Research demo Bandwidth limits and compartmentalization Add
  • Bounding unexplained information in outputs waits on it. The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.
• Proposed Side-channel suppression for isolated facilities Add
  • Bounding unexplained information in outputs waits on it. Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target.
• Operational use Sampled inference recomputation Add
  • Bounding unexplained information in outputs depends on it.
• Proposed Network taps and certifiers Add
  • Bounding unexplained information in outputs depends on it.

Missing prerequisites

• Operational use TEE remote attestation for AI workloads needed by Safeguard attestation and On-chip telemetry from timing, memory and performance counters Add
• Operational use Hardware-attested weight binding needed by Safeguard attestation Add
• Operational use Sampled inference recomputation needed by Bounding unexplained information in outputs Add
• Research demo Bandwidth limits and compartmentalization needed by Bounding unexplained information in outputs Add
• Proposed Side-channel suppression for isolated facilities needed by Bounding unexplained information in outputs Add
• Proposed Network taps and certifiers needed by Bounding unexplained information in outputs Add

Shared foundations

• TEE remote attestation for AI workloads relied on by Safeguard attestation and On-chip telemetry from timing, memory and performance counters

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 22}
  • 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 ^{22 23}
  • 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}
• Bounding unexplained information in outputs
  • The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound. Coverage & hidden compute. Waits on Bandwidth limits and compartmentalization ¹⁴
  • Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ^{13 15}
  • Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata. Protocol soundness. Waits on Deterministic and bit-exact inference ^{13 16}
  • Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs. Privacy & leakage ¹⁴
  • No prototype of the facility-level architecture exists to red-team. Adversarial validation ¹⁴
• On-chip telemetry from timing, memory and performance counters
  • Shipping accelerators need a tamper-resistant, authenticated telemetry path. Hardware trust. Waits on Hardware-enabled guarantees (flexHEG) and guarantee processors ^{19 20}
  • NVIDIA's full confidential-computing mode disables the hardware performance counters its profiling tools use, so telemetry that needs them conflicts with it. Privacy & leakage ^{9 21}
  • Continuous challenge puzzles cost power and throughput on production workloads. Performance & compatibility ¹⁸
  • Evaluation has not gone beyond single nodes, framework-level evasion and one vendor's hardware. Adversarial validation ²⁰

From the family or selected implementation's record. ?

Model weights

Depends on the design for Safeguard attestation, Bounding unexplained information in outputs and On-chip telemetry from timing, memory and performance counters.

Inputs and outputs

Depends on the design for Safeguard attestation, Bounding unexplained information in outputs and On-chip telemetry from timing, memory and performance counters.

Training data

Depends on the design for On-chip telemetry from timing, memory and performance counters.

Not involved: Safeguard attestation and Bounding unexplained information in outputs.

Safeguard attestation

None on the map

Bounding unexplained information in outputs

None on the map

On-chip telemetry from timing, memory and performance counters

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. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). Original
15. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
16. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
17. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). Original
18. Timing and Memory Telemetry on GPUs for AI Governance, S. K. Monfared et al. (2026). Original
19. Guaranteeable Memory: An HBM-Based Chiplet for Verifiable AI Workloads, J. Petrie (2025). Original
20. Detecting Hidden ML Training With Zero-Overhead Telemetry, R. Rahman & S. Tajdari (2026). Original
21. NVIDIA Secure AI with Blackwell and Hopper GPUs (White Paper), NVIDIA (2025). Original
22. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
23. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original