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

Zero-knowledge proofs of inference and Sampled inference recomputation

No new hardware needed

Zero-knowledge proofs of inference and Sampled inference recomputation

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
• Sampled inference recomputation: Analysis

Open significant failures

2 failures in 1 mechanism

• 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. ^{13 21 24}

  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. ^{14 15}

  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

• 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. ^{13 25}

  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. Add

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. ¹⁴

  Known failure · Open question · Minor · Open. 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 “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.
• Proposed Network taps and certifiers Add
  • Sampled inference recomputation waits on it. 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.
• 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.

Blockers

9 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
• 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 ^{20 26}
  • 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 ^{13 20}
  • 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 ^{20 21}
  • 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 ^{14 19}
  • 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 ^{11 14 25}

From the family or selected implementation's record. ?

Model weights

Depends on the design for Sampled inference recomputation.

Hidden by Zero-knowledge proofs of inference.

Inputs and outputs

Shown by Zero-knowledge proofs of inference.

Depends on the design for Sampled inference recomputation.

Training data

Not involved: Zero-knowledge proofs of inference and Sampled inference recomputation.

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

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

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. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
14. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
15. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
16. PrimeIntellect-ai/toploc (GitHub repository), Prime Intellect (2025). Original
17. INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning, Prime Intellect Team et al. (2025). Original
18. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
19. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
20. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
21. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
22. SYNTHETIC-2 Release: Four Million Collaboratively Generated Reasoning Traces, Prime Intellect (2025). Original
23. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
24. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
25. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
26. Verification Plan, R. Dean (2026). Original