Proposal Explorer

Add claims to see which ones the mechanisms address.

Operational use

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

Built for an adversarial prover

Memory wiping and proofs of secure erasure, Bandwidth limits and compartmentalization, Sampled inference recomputation and Network taps and certifiers

No new hardware needed

Memory wiping and proofs of secure erasure and Sampled inference recomputation

Failures since mitigated

• Verifier dictionary attacks on hashes in Network taps and certifiers ²⁷

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.

• Memory wiping and proofs of secure erasure: Analysis
• Bandwidth limits and compartmentalization: Analysis
• Sampled inference recomputation: Analysis
• Network taps and certifiers: Analysis

Open significant failures

7 failures in 4 mechanisms

• Outside help during challenges in Memory wiping and proofs of secure erasure

  Classic proofs of secure erasure assume the device is isolated during the protocol. Bursuc et al. relax this to a bound on how close a helper can be, enforced by round-trip times. In data centres, remote memory access has round trips of about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview therefore says verification depends on ruling out RDMA by latency or physical disconnection. ^{3 4}

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

  Related mechanism Research demo Timed challenge-response and memory-occupation challenges: Timed challenges bound how far away a helper can be by how quickly it must answer. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Research demo Bandwidth limits and compartmentalization: Removing or capping links between groups of accelerators limits remote memory access during a challenge. A pointer, not evidence that this failure is mitigated. In the proposal.

• 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. ⁹

  Known failure · Theoretical argument · 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. ¹¹

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

• 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. ^{14 22 25}

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

  Related mechanism Operational use 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 failure is mitigated. Add

• 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. ^{15 16}

  Known failure · 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. ^{22 27}

  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. Add

• 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. ²⁹

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

Scope limitations

• Memory the wipe cannot reach in Memory wiping and proofs of secure erasure

  Amodo's inventory of a GB200 system lists many memory stores beyond GPU HBM and host DRAM. It notes that SSD controller DRAM sits on a private bus that host commands cannot read or write, and that its optimized algorithm leaves 25 GiB of HBM unattested. It also asks how switch memory could be wiped. ^{5 6}

  Scope limitation · Open question. On the record

• Gap between erased and total memory in Memory wiping and proofs of secure erasure

  Bursuc et al. note that memory left between the erased region and the device's full memory could hold data, and that their bounds are tighter only against a restricted adversary. ³

  Scope limitation · Theoretical argument. 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. ⁹

  Scope limitation · Theoretical argument. 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. ⁹

  Scope limitation · Open question. On the record

• 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. ^{14 26}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed 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 failure 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. ^{28 33}

  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. ²⁸

  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. ²⁷

  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

• 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. ^{9 12 13}

  Open question · Theoretical argument. On the record

Open minor failures

1 mechanism with minor failures

• 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. ¹⁵

  Known failure · Open question · Minor · Open. On the record

Not yet demonstrated

Proposed Memory wiping and proofs of secure erasure 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 “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.
  • 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.
  • Network taps and certifiers waits on it. Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.
• Research demo Bounding unexplained information in outputs Add
  • Bears on the open significant failure “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict.
• Research demo Timed challenge-response and memory-occupation challenges Add
  • Bears on the open significant failure “Outside help during challenges” in Memory wiping and proofs of secure erasure. Timed challenges bound how far away a helper can be by how quickly it must answer.
  • Memory wiping and proofs of secure erasure waits on it. Timed challenges must exclude remote memory and other helpers.
• Research demo 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.
• Proposed Side-channel suppression for isolated facilities Add
  • Network taps and certifiers waits on it. Radio, power-line and thermal channels are not addressed by network-level designs.

Missing prerequisites

• Research demo Timed challenge-response and memory-occupation challenges needed by Memory wiping and proofs of secure erasure Add
• Research demo Tamper evidence for verifier devices needed by Bandwidth limits and compartmentalization and Network taps and certifiers Add
• Operational use Deterministic and bit-exact inference needed by Network taps and certifiers Add
• Proposed Side-channel suppression for isolated facilities needed by Network taps and certifiers Add

Shared foundations

• Tamper evidence for verifier devices relied on by Bandwidth limits and compartmentalization and Network taps and certifiers
• Network taps and certifiers relied on by Bandwidth limits and compartmentalization and Sampled inference recomputation. In the proposal

Blockers

17 blockers recorded

• Memory wiping and proofs of secure erasure
  • Wipes take time: tens of minutes for a pod's volatile memory and hours for SSDs, displacing work. Performance & compatibility ^{4 5 6}
  • Timed challenges must exclude remote memory and other helpers. Coverage & hidden compute. Waits on Timed challenge-response and memory-occupation challenges ^{3 4}
  • All memory stores in a system must be inventoried and wiped at the same time. Coverage & hidden compute ⁵
• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ⁹
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ⁴
  • 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 ^{9 11}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{9 12 13}
• 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 ^{1 21}
  • 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 ^{14 21}
  • 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 ^{21 22}
  • 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 ^{15 20}
  • 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 ^{4 15 26}
• 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 ^{33 34}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ²⁷
  • 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 ^{4 27}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ²⁷
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ²⁷

From the family or selected implementation's record. ?

Model weights

Depends on the design for Sampled inference recomputation and Network taps and certifiers.

Not involved: Memory wiping and proofs of secure erasure and Bandwidth limits and compartmentalization.

Inputs and outputs

Depends on the design for Sampled inference recomputation and Network taps and certifiers.

Not involved: Memory wiping and proofs of secure erasure and Bandwidth limits and compartmentalization.

Training data

Depends on the design for Network taps and certifiers.

Not involved: Memory wiping and proofs of secure erasure, Bandwidth limits and compartmentalization and Sampled inference recomputation.

Memory wiping and proofs of secure erasure

• 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

Bandwidth limits and compartmentalization

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

Sampled inference recomputation

• Proposed AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• Research demo DiFR (Divergence From Reference) Research prototype
• 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)
• Operational use TOPLOC Open-source project, Prime Intellect

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. Verification Plan, R. Dean (2026). Original
2. Secure Code Update for Embedded Devices via Proofs of Secure Erasure, D. Perito & G. Tsudik (2010). Original
3. Software-Based Memory Erasure with Relaxed Isolation Requirements, S. Bursuc et al. (2024). Original
4. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
5. Memory Wipes - Performance Analysis, Amodo Design (2026). Original
6. Improving Disk Wiping Speed for Memory Wipes, Amodo Design (2026). Original
7. Amodo-Design/PoSE-Memory-Wiping (GitHub repository), Amodo Design (2026). Original
8. Empirical Evaluation of Memory-Erasure Protocols, R. Gil-Pons et al. (2025). Original
9. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
10. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
11. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
12. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
13. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
14. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
15. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
16. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
17. PrimeIntellect-ai/toploc (GitHub repository), Prime Intellect (2025). Original
18. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning, Prime Intellect Team et al. (2025). Original
19. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
20. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
21. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
22. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
23. SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces, Prime Intellect (2025). Original
24. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
25. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
26. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
27. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
28. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). Original
29. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
30. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
31. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). Original
32. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). Original
33. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). Original
34. Network Traffic Hashing, Amodo Design (2026). Original