Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Remote detection of data centres, Bounding unexplained information in outputs and Network taps and certifiers

No new hardware needed

Remote detection of data centres

Failures since mitigated

• Verifier dictionary attacks on hashes in Network taps and certifiers ¹¹

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.

• Remote detection of data centres: Analysis
• Bounding unexplained information in outputs: Independent red-team
• Network taps and certifiers: Analysis

Open significant failures

3 failures in 2 mechanisms

• 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. ^{7 8}

  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

• Output nondeterminism leaves covert capacity in Network taps and certifiers

  Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs. ^{8 11}

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

  Related mechanism Operational use Deterministic and bit-exact inference: Deterministic replay is one of the two remedies the flaw's source names. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Research demo Bounding unexplained information in outputs: Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict. A pointer, not evidence that this failure is mitigated. In the proposal.

• Residual side channels in simple passive setups in Network taps and certifiers

  Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one. ¹⁴

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

Scope limitations

• 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. ¹

  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. ^{1 3}

  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

• 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. ^{6 9}

  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. ^{7 10}

  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

• Some links cannot be passively tapped in Network taps and certifiers

  Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026. ^{12 18}

  Scope limitation · Open question. On the record

• Encrypted fabrics hide plaintext from both parties in Network taps and certifiers

  Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys. ¹²

  Scope limitation · Open question. On the record

• Completeness rests on physical monitoring left out of scope in Network taps and certifiers

  The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope. ¹¹

  Scope limitation · Open question. On the record

  Related mechanism Proposed Side-channel suppression for isolated facilities: Addresses the radio, power-line and thermal channels that network-level designs leave out. A pointer, not evidence that this failure is mitigated. Add

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". ³

  Open question · Open question. On the record

• 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. ⁶

  Open question · Open question. On the record

Not yet demonstrated

Proposed Remote detection of data centres and Proposed Network taps and certifiers

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.
  • Bears on the open significant failure “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Deterministic replay is one of the two remedies the flaw's source names.
  • 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.
  • Network taps and certifiers waits on it. Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.
• 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.
• Research demo Tamper evidence for verifier devices Add
  • Network taps and certifiers waits on it. Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.
• 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.
  • Network taps and certifiers waits on it. Radio, power-line and thermal channels are not addressed by network-level designs.
• Operational use Sampled inference recomputation Add
  • Bounding unexplained information in outputs depends on it.
  • Network taps and certifiers depends on it.

Missing prerequisites

• Operational use Sampled inference recomputation needed by Bounding unexplained information in outputs and Network taps and certifiers 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 and Network taps and certifiers Add
• Operational use Deterministic and bit-exact inference needed by Network taps and certifiers Add
• Research demo Tamper evidence for verifier devices needed by Network taps and certifiers Add

Shared foundations

• Sampled inference recomputation relied on by Bounding unexplained information in outputs and Network taps and certifiers
• Side-channel suppression for isolated facilities relied on by Bounding unexplained information in outputs and Network taps and certifiers
• Deterministic and bit-exact inference relied on by Bounding unexplained information in outputs and Network taps and certifiers

Blockers

13 blockers recorded

• Remote detection of data centres
  • Wide-area, automated detection of data centres is not yet practical and needs large training datasets. Coverage & hidden compute ³
  • No measured detection or false-alarm rates for finding undeclared facilities have been published. Adversarial validation ^{1 3}
  • Recent high-resolution imagery is costly, is limited by weather and needs trained analysts. Access & governance ³
• 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 ⁶
  • 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 ^{7 10}
  • 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 ^{8 10}
  • 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 ⁶
  • No prototype of the facility-level architecture exists to red-team. Adversarial validation ⁶
• Network taps and certifiers
  • No complete verification tap has been demonstrated at production frontend link rates, and on the tested CPU no hash algorithm reached line rate with minimum-size frames. Performance & compatibility ^{18 19}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ¹¹
  • Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them. Hardware trust. Waits on Tamper evidence for verifier devices ^{10 11}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ¹¹
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ¹¹

From the family or selected implementation's record. ?

Model weights

Depends on the design for Bounding unexplained information in outputs and Network taps and certifiers.

Not involved: Remote detection of data centres.

Inputs and outputs

Depends on the design for Bounding unexplained information in outputs and Network taps and certifiers.

Not involved: Remote detection of data centres.

Training data

Depends on the design for Network taps and certifiers.

Not involved: Remote detection of data centres and Bounding unexplained information in outputs.

Remote detection of data centres

None on the map

Bounding unexplained information in outputs

None on the map

Network taps and certifiers

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

1. Covert AI Projects, B. Halstead & T. Larsen (2026). Original
2. Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment, M. Baker et al. (2025). Original
3. Tracking Hyperscale AI Data Center Growth with Satellite Imagery, C. Krawec (2026). Original
4. Introducing the Frontier Data Centers Hub, Epoch AI (2025). Original
5. AI Data Centers Documentation – Methodology, Epoch AI (2026). Original
6. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). Original
7. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
8. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
9. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). Original
10. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
11. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
12. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). Original
13. Verification Plan, R. Dean (2026). Original
14. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
15. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
16. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). Original
17. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). Original
18. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). Original
19. Network Traffic Hashing, Amodo Design (2026). Original