Proposal Explorer

Add claims to see which ones the mechanisms address.

Operational use

• Operational use Deterministic and bit-exact inference for reproducing open-model inference from receipts in Gensyn's information-market service

Built for an adversarial prover

Zero-knowledge proofs of inference, Network taps and certifiers, Remote detection of data centres and Deterministic and bit-exact inference

No new hardware needed

Zero-knowledge proofs of inference, Remote detection of data centres and Deterministic and bit-exact inference

Failures since mitigated

• Verifier dictionary attacks on hashes in Network taps and certifiers ¹³

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.

• Zero-knowledge proofs of inference: Independent red-team
• Network taps and certifiers: Analysis
• Remote detection of data centres: Analysis
• Deterministic and bit-exact inference: Analysis

Open significant failures

2 failures in 1 mechanism

• 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. ^{13 20}

  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. In the proposal.

  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. ¹⁶

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

Scope limitations

• The proof covers a fixed-point approximation, not the floating-point model in Zero-knowledge proofs of inference

  Current ZK inference systems prove a quantised version of the network. zkLLM scales values by 2^16 and reports small perplexity changes. Attestable reports quantising matrix multiplications to 8-bit integers while proving other operations in floating point. A verifier therefore learns about the proof-friendly variant, and must separately accept that this variant is the declared model. Trail of Bits built a ResNet-18 backdoor that is dormant in the full-precision model and active after ezkl's quantisation; whether it persists through proving was left for further investigation. A verification system design notes that ZKPs can emulate floating-point operations. Rounding makes floating-point results depend on summation order, so bit-for-bit replay of an accelerator's results needs its original reduction tree. The report calls emulating that tree inside a ZKP an open, intricate problem and asks what it would cost. ^{1 5 7 11}

  Scope limitation · Open question. On the record

• A proof speaks only for the computations that were proven in Zero-knowledge proofs of inference

  Attestable writes that "a proof of some computation is not a proof of all computation", and that a proof cannot discover a datacenter that was never declared. Proofs of inference do not by themselves show that no other workload ran on the same or other hardware. ¹²

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Proofs of useful work for capacity accounting: The record names proof-of-work accounting as the kind of compute accounting needed to show that proven inference was the only work done. A pointer, not evidence that this failure is mitigated. Add

• The model architecture is disclosed in Zero-knowledge proofs of inference

  ZKML "requires that the model architecture (but not weights) is revealed", and zkLLM assumes a publicly known model structure. Architecture can be commercially sensitive. ^{1 3}

  Scope limitation · Theoretical argument. On the record

• Proofs do not bind computational effort (Hollow-LLM) in Zero-knowledge proofs of inference

  Researchers at the University of Southern California show that a proof of inference certifies that an output is consistent with committed weights under the declared architecture, but not how much computation produced it. In their Hollow-LLM attack, a provider keeps the declared architecture and parameter count but commits to "ghost weights". Some layers pass their inputs through unchanged, and wide layers carry the signal in a small subspace, so a much smaller inner model does the real work. The ghost weights satisfy the verification circuit and yield valid proofs.

  The authors ran the attack with the proof procedure of zkGPT, a separate ZK inference system, on a 6-layer, 512-dimensional transformer declared as up to 12 layers and 1,024 dimensions. Outputs were identical to the inner model's, and serving cost stayed at the inner model's level. An honest model of the declared size cost 2.4 times as much to prefill and 3.1 times as much to decode. Proving cost still grew with the declared architecture.

  The authors note that results may be served before any proof, with the provider building the witness only when a call is selected for audit. They describe their constructions as "compatible with state-of-the-art zkLLM pipelines", and state that the attack does not imply a flaw in the proof system itself. They propose challenge-based audits and ablation tests, which raise the cost of cheating but give no guarantee. ¹⁰

  Scope limitation · Demonstrated attack. On the record

• 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. ^{14 21}

  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. ¹⁴

  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. ¹³

  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

• 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. ²²

  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. ^{22 24}

  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

• Some kernels remain genuinely nondeterministic in Deterministic and bit-exact inference

  The bit-exact work separates kernels that are deterministic but not batch-invariant from truly nondeterministic ones that use atomic functions. Some integer de-quantization kernels use atomic additions and remain nondeterministic, so exact replay needs backends that avoid them. ²⁷

  Scope limitation · Open question. On the record

• Cross-hardware replay relies on reverse-engineered, closed behaviour in Deterministic and bit-exact inference

  Emulating one GPU's rounding on another requires reverse-engineering tensor-core arithmetic and modelling proprietary kernel choices. Hawkeye covers a subset of NVIDIA architectures and states that attention and other higher-level operations need further reverse engineering. For the bit-exact emulator, a proprietary Hopper kernel family is an open edge case. ^{27 29}

  Scope limitation · Open question. On the record

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". ²⁴

  Open question · Open question. On the record

Not yet demonstrated

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

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

• 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 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 Proofs of useful work for capacity accounting Add
  • Zero-knowledge proofs of inference waits on it. Showing that proven inference was the only work done needs a compute-accounting mechanism such as proof-of-work accounting, which is only proposed.
• 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.
• Operational use Sampled inference recomputation Add
  • Network taps and certifiers depends on it.

Missing prerequisites

• Operational use Sampled inference recomputation needed by Network taps and certifiers Add
• Research demo Tamper evidence for verifier devices needed by Network taps and certifiers Add
• Proposed Side-channel suppression for isolated facilities needed by Network taps and certifiers Add

Blockers

16 blockers recorded

• Zero-knowledge proofs of inference
  • Proving takes about 13 minutes (803 seconds) per 2,048-token forward pass of a 13B model on one A100, and a verification system design calls the overhead heavy. Performance & compatibility ^{1 11}
  • ZKML and zkLLM prove fixed-point arithmetic, and a verification system design calls emulating an accelerator's original floating-point reduction tree inside a zero-knowledge proof, which bit-for-bit replay needs, an open and intricate problem whose cost is also unsettled. Performance & compatibility ^{1 3 11}
  • zkLLM's code is unaudited, interactive and archived; the one audited ZK inference library, ezkl, had high-severity circuit soundness bugs before its fixes. Adversarial validation ^{2 7}
  • Showing that proven inference was the only work done needs a compute-accounting mechanism such as proof-of-work accounting, which is only proposed. Coverage & hidden compute. Waits on Proofs of useful work for capacity accounting ¹²
• 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 ^{21 37}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ¹³
  • 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 ^{11 13}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ¹³
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ¹³
• Remote detection of data centres
  • Wide-area, automated detection of data centres is not yet practical and needs large training datasets. Coverage & hidden compute ²⁴
  • No measured detection or false-alarm rates for finding undeclared facilities have been published. Adversarial validation ^{22 24}
  • Recent high-resolution imagery is costly, is limited by weather and needs trained analysts. Access & governance ²⁴
• Deterministic and bit-exact inference
  • Batch-invariant kernels cost throughput: in Thinking Machines' Qwen3-8B test, an improved deterministic build took 42 s against 26 s for vLLM's default, and SGLang reports an average 34.35% slowdown on its FlashInfer and FlashAttention 3 backends. Performance & compatibility ^{28 30}
  • Coverage is incomplete: the bit-exact emulator targets dense blocks on NVIDIA GPUs and excludes mixture-of-experts inference and training, and vLLM's batch-invariant mode is in beta, with open work on AMD hardware and speculative decoding. Performance & compatibility ^{27 31 38}
  • Amodo's status page for the AI 2040 verification plan rates a reproducible inference stack for that plan as 'not started'. Performance & compatibility ³⁹
  • Exact replay requires the prover to disclose weights, software versions, parallelism and batch sizes to whoever recomputes. Privacy & leakage ^{11 27}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Network taps and certifiers and Deterministic and bit-exact inference.

Hidden by Zero-knowledge proofs of inference.

Not involved: Remote detection of data centres.

Inputs and outputs

Shown by Zero-knowledge proofs of inference.

Depends on the design for Network taps and certifiers and Deterministic and bit-exact inference.

Not involved: Remote detection of data centres.

Training data

Depends on the design for Network taps and certifiers.

Not involved: Zero-knowledge proofs of inference, Remote detection of data centres and Deterministic and bit-exact inference.

Zero-knowledge proofs of inference

• Proposed Attestable zero-knowledge inference prover Product, Attestable
• Research demo EZKL Product, Zkonduit
• Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• Research demo zkLLM Research prototype, University of Waterloo

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)

Remote detection of data centres

None on the map

Deterministic and bit-exact inference

• Research demo Batch-invariant inference kernels (Thinking Machines) Open-source project, Thinking Machines Lab
• Operational use Verde and RepOps (Gensyn) Product, Gensyn
• Proposed Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute

1. zkLLM: Zero Knowledge Proofs for Large Language Models, H. Sun et al. (2024). Original
2. zkllm-ccs2024: code for zkLLM: Zero Knowledge Proofs for Large Language Models, H. Sun (2024). Original
3. ZKML: An Optimizing System for ML Inference in Zero-Knowledge Proofs, B.-J. Chen et al. (2024). Original
4. NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs, Z. Wang (2026). Original
5. Proving LLMs at Scale, Attestable (2026). Original
6. Verifiable evaluations of machine learning models using zkSNARKs, T. South et al. (2024). Original
7. Zkonduit EZKL Security Assessment, F. Casal et al. (2025). Original
8. DeepProve-1: The First zkML System to Prove a Full LLM Inference, Lagrange Labs (2025). Original
9. Lagrange-Labs/deep-prove (GitHub repository), Lagrange Labs (2026). Original
10. Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference, C. Gong et al. (2026). Original
11. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
12. Pacing AI Requires Proof, Attestable (2026). Original
13. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
14. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). Original
15. Verification Plan, R. Dean (2026). Original
16. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
17. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
18. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). Original
19. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). Original
20. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
21. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). Original
22. Covert AI Projects, B. Halstead & T. Larsen (2026). Original
23. Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment, M. Baker et al. (2025). Original
24. Tracking Hyperscale AI Data Center Growth with Satellite Imagery, C. Krawec (2026). Original
25. Introducing the Frontier Data Centers Hub, Epoch AI (2025). Original
26. AI Data Centers Documentation – Methodology, Epoch AI (2026). Original
27. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
28. Defeating Nondeterminism in LLM Inference, H. He & Thinking Machines Lab (2025). Original
29. Hawkeye: Reproducing GPU-Level Non-Determinism, E. Badash et al. (2026). Original
30. Towards Deterministic Inference in SGLang and Reproducible RL Training, The SGLang Team (2025). Original
31. Batch Invariance (vLLM documentation), vLLM project (2026). Original
32. gensyn-ai/ree: Gensyn Reproducible Execution Environment (GitHub repository), Gensyn (2026). Original
33. EigenCloud Brings Verifiable AI to Mass Market with EigenAI and EigenCompute Launches, EigenCloud (2025). Original
34. Building Delphi: Pricing, Settlement, and Agentic Trading, D. Jedamski (2026). Original
35. Reproducible Execution Environment (REE) (Gensyn documentation), Gensyn (2026). Original
36. What is Delphi? (Delphi documentation), Gensyn (2026). Original
37. Network Traffic Hashing, Amodo Design (2026). Original
38. [Feature]: Batch Invariant Feature and Performance Optimization (vLLM issue #27433), vLLM project contributors (2025). Original
39. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original