Proposal Explorer

Add claims to see which ones the mechanisms address.

In production

• R3 Sampled inference recomputation for checking untrusted workers' activations against the declared model, prompt and precision

Built for an adversarial prover

Bounding unexplained information in outputs, Bandwidth limits and compartmentalization, Network taps and certifiers and Sampled inference recomputation

No new hardware needed

Sampled inference recomputation

Flaws since mitigated

• Verifier dictionary attacks on hashes in Network taps and certifiers ¹²

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

• Bounding unexplained information in outputs: Independent red-team
• Bandwidth limits and compartmentalization: Analysis
• Network taps and certifiers: Analysis
• Sampled inference recomputation: Analysis

Open significant flaws

17 flaws in 4 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. ^{2 3}

  Demonstrated attack · Significant · Open. On the record

  Related mechanism R3 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 flaw 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. ^{1 4}

  Theoretical argument · Significant · Open. 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. ^{2 5}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R1 Side-channel suppression for isolated facilities: Physical side channels need separate suppression, which is this mechanism's purpose. A pointer, not evidence that this flaw is mitigated. Add

• 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. ¹

  Open question · Significant · Open. On the record

• Low-communication training reduces the bandwidth training needs in Bandwidth limits and compartmentalization

  DiLoCo matched fully synchronous training on 8 workers while communicating 500 times less. Rahman writes that this family of methods theoretically allows large-scale training with less than 100 Mbps. Lucid includes these methods in its bounds, but notes that extreme activation compression, architectures with unusually small inter-layer widths, or modular paradigms could erode the margin. ^{7 10 11}

  Theoretical argument · Significant · Open. On the record

• Operator control of pod routing collapses the bound in Bandwidth limits and compartmentalization

  Lucid's analysis finds that if the operator can freely assign pods to routers, it could dedicate a whole cell of 100 or more pods to one pipeline stage. The bound then falls to about 90–220x uncompressed and as low as about 25x with compression. The proposed mitigation, auditor-controlled random assignment that is periodically re-randomized, has not been implemented. ⁷

  Theoretical argument · Significant · Open. On the record

• Undeclared local storage raises per-pod capacity in Bandwidth limits and compartmentalization

  More memory or storage per pod helps an adversary. Lucid requires per-pod storage to be declared, capped and physically inspected. ⁷

  Theoretical argument · Significant · Open. On the record

• Training within one pod is not covered in Bandwidth limits and compartmentalization

  Lucid's bounds concern pre-training models larger than the pods are sized for. Training models that fit in one pod, fine-tuning and reinforcement-learning post-training within one pod are outside the modelled threat. ⁷

  Open question · Significant · Open. On the record

• Parallel scale-up switches are hard enforcement points in Bandwidth limits and compartmentalization

  In GB200 topologies, GPUs reach GPUs in other nodes through NVSwitches without a NIC on the path. Amodo notes that limits are hard to enforce there because many switches work in parallel, so compromising one or two would bypass the limit. ⁹

  Theoretical argument · Significant · Open. On the record

• 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. ^{3 12}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R3 Deterministic and bit-exact inference: Deterministic replay is one of the two remedies the flaw's source names. A pointer, not evidence that this flaw is mitigated. Add

  Related mechanism R2 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 flaw is mitigated. In the proposal.

• 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. ^{13 18}

  Open question · Significant · Open. 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. ¹³

  Open question · Significant · Open. On the record

• 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

  Theoretical argument · Significant · Open. 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. ¹²

  Open question · Significant · Open. On the record

  Related mechanism R1 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 flaw is mitigated. Add

• 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. ^{2 3 28}

  Demonstrated attack · Significant · Open. On the record

  Related mechanism R3 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 flaw 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. ^{2 29}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R1 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 flaw is mitigated. In the proposal.

• 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. ^{19 20}

  Theoretical argument · Significant · Open. On the record

Open minor flaws

1 mechanism with minor findings

• 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. ¹⁹

  Open question · Minor · Open. On the record

Not yet demonstrated

R1 Network taps and certifiers

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

• R3 Deterministic and bit-exact inference Add
  • Bears on the open significant flaw “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 flaw “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Deterministic replay is one of the two remedies the flaw's source names.
  • Bears on the open significant flaw “Tolerance for numerical noise leaves a covert channel” in Sampled inference recomputation. Bit-exact inference would remove the numerical tolerance if exact replay can be deployed with the required weights and configuration.
  • 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.
• R1 Side-channel suppression for isolated facilities Add
  • Bears on the open significant flaw “Channels other than checked outputs are outside the bound” in Bounding unexplained information in outputs. Physical side channels need separate suppression, which is this mechanism's purpose.
  • Bears on the open significant flaw “Completeness rests on physical monitoring left out of scope” in Network taps and certifiers. Addresses the radio, power-line and thermal channels that network-level designs leave out.
  • 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.
• R2 Tamper evidence for verifier devices Add
  • Bandwidth limits and compartmentalization waits on it. Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU.
  • Network taps and certifiers waits on it. Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.

Missing prerequisites

• R1 Side-channel suppression for isolated facilities needed by Bounding unexplained information in outputs and Network taps and certifiers Add
• R2 Tamper evidence for verifier devices needed by Bandwidth limits and compartmentalization and Network taps and certifiers Add
• R3 Deterministic and bit-exact inference needed by Network taps and certifiers Add

Shared foundations

• Network taps and certifiers relied on by Bounding unexplained information in outputs, Bandwidth limits and compartmentalization and Sampled inference recomputation. In the proposal
• Sampled inference recomputation relied on by Bounding unexplained information in outputs and Network taps and certifiers. In the proposal
• 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
• Tamper evidence for verifier devices relied on by Bandwidth limits and compartmentalization and Network taps and certifiers

Blockers

19 blockers recorded

• 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 ¹
  • 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 ^{2 5}
  • 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 ^{3 5}
  • 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 ¹
  • No prototype of the facility-level architecture exists to red-team. Adversarial validation ¹
• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ⁷
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ⁵
  • Shaping devices and routing assignments must be trusted by both parties; Amodo has not yet fully analysed resilience to a compromised DPU. Hardware trust. Waits on Tamper evidence for verifier devices ^{7 9}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{7 10 11}
• 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 30}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ¹²
  • 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 ^{5 12}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ¹²
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ¹²
• Sampled inference recomputation
  • In tap-based retrofit designs, recording all inference traffic needs network taps and recomputation servers that can ingest it, in the worst case one recomputation-server network interface per inference front-end interface. Coverage & hidden compute. Waits on Network taps and certifiers ^{6 25}
  • In retrofit designs, the recomputation server must sit inside the prover's data centre, possibly under the prover's physical control, and still be protected from a compromised provider, which Amodo rates 'not on track'. Hardware trust ^{2 25}
  • No independent red-team of a recomputation consistency check has been published (the one independent attack study targets the weight-exfiltration bound), and Amodo rates recomputation red-teaming 'not started'. Adversarial validation ^{3 25}
  • Tolerance-based checks need calibration on trusted hardware and exact knowledge of the provider's sampling procedure, and in one prototype a sampling-implementation mismatch produced large spurious differences. Performance & compatibility ^{19 24}
  • The verifier needs the model weights, so checking a closed-weights model requires a trusted, confidential recomputation environment, which the retrofit designs place inside the prover's facility. Privacy & leakage ^{5 19 29}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Bounding unexplained information in outputs, Network taps and certifiers and Sampled inference recomputation.

Not involved: Bandwidth limits and compartmentalization.

Inputs and outputs

Depends on the design for Bounding unexplained information in outputs, Network taps and certifiers and Sampled inference recomputation.

Not involved: Bandwidth limits and compartmentalization.

Training data

Depends on the design for Network taps and certifiers.

Not involved: Bounding unexplained information in outputs, Bandwidth limits and compartmentalization and Sampled inference recomputation.

Bounding unexplained information in outputs

None on the map

Bandwidth limits and compartmentalization

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R1 RAND secure inference data center (SIDC) design Proposed architecture, RAND

Network taps and certifiers

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• R1 SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)

Sampled inference recomputation

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R2 DiFR (Divergence From Reference) Research prototype
• R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• R1 SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)
• R3 TOPLOC Open-source project, Prime Intellect

1. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). Original
2. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
3. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
4. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). Original
5. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
6. Verification Plan, R. Dean (2026). Original
7. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
8. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
9. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
10. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
11. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
12. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
13. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (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. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
20. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
21. PrimeIntellect-ai/toploc (GitHub repository), Prime Intellect (2025). Original
22. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning, Prime Intellect Team et al. (2025). Original
23. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
24. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
25. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
26. SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces, Prime Intellect (2025). Original
27. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
28. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
29. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
30. Network Traffic Hashing, Amodo Design (2026). Original