Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Zero-knowledge proofs of inference and Bandwidth limits and compartmentalization

No new hardware needed

Zero-knowledge proofs of inference

Not counted

Excluded by your filters: Proofs of useful work for capacity accounting

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
• Bandwidth limits and compartmentalization: Analysis
• Proofs of useful work for capacity accounting: Analysis · excluded by filters

Excluded by your filters

• Proofs of useful work for capacity accounting Development status: Proposed. Minimum: Research demonstration.

Open significant failures

3 failures in 2 mechanisms

• 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. ¹⁴

  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. ¹⁶

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

• Known shortcuts let a miner claim somewhat more work than it did in Proofs of useful work for capacity accounting

  Pearl's specification lists known mining speedups: crafted inputs, precision shortcuts, seed grinding, work reuse, and faster kernels or hardware. A policy check caps the summands a miner may skip at one-sixteenth of those in a tile. For capacity bounding, any gap between work proven and work possible leaves spare capacity. ²¹

  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. In the proposal.

• 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

• 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. ¹⁴

  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. ¹⁴

  Scope limitation · Open question. On the record

• Proves that work was done, not that no capacity remains in Proofs of useful work for capacity accounting

  Proof-of-work accounting bounds unmonitored compute only relative to an estimate of what the actor has. Attestable states that the verifier "needs a credible estimate of the compute available" to the actor, and that a proof "cannot discover a datacenter that was never declared". ¹²

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Chip registries and manufacturing records: A registry of chips is one basis for the estimate of available compute that the flaw's source says the verifier needs. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Proposed Remote detection of data centres: Looks for data centres that were never declared, which a proof cannot discover. 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. ^{14 17 18}

  Open question · Theoretical argument. On the record

• Security rests on new hardness assumptions in Proofs of useful work for capacity accounting

  Komargodski and Weinstein base security on hardness assumptions about batches of low-rank random linear equations, and list PoUW "from more standard or well-studied assumptions" as an open problem. Pearl's floating-point variant introduces a further "quantized-subspace hardness" assumption. ^{20 21}

  Open question · Open question. On the record

Not yet demonstrated

Proposed Proofs of useful work for capacity accounting

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

• 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.
• Proposed Network taps and certifiers Add

  Excluded by filters: development: Proposed

  • Bandwidth limits and compartmentalization waits on it. The verifier must know that all traffic leaving a pod crosses the capped, monitored links.

Missing prerequisites

• Research demo Tamper evidence for verifier devices needed by Bandwidth limits and compartmentalization Add

Blockers

11 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
• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ¹⁴
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ¹¹
  • 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 ^{14 16}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{14 17 18}
• Proofs of useful work for capacity accounting
  • Bounding spare capacity needs a credible estimate of the compute available to the actor, including third-party access. Capacity bounds ¹²
  • Proofs of work cannot find facilities that were never declared. Coverage & hidden compute ¹²
  • As of September 2026 no implementation, demonstration or independent evaluation of proofs of work for capacity bounding has been published. Adversarial validation

From the family or selected implementation's record. ?

Model weights

Depends on the design for Proofs of useful work for capacity accounting.

Hidden by Zero-knowledge proofs of inference.

Not involved: Bandwidth limits and compartmentalization.

Inputs and outputs

Shown by Zero-knowledge proofs of inference.

Depends on the design for Proofs of useful work for capacity accounting.

Not involved: Bandwidth limits and compartmentalization.

Training data

Not involved: Zero-knowledge proofs of inference, Bandwidth limits and compartmentalization and Proofs of useful work for capacity accounting.

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

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

Proofs of useful work for capacity accounting

• Operational use Pearl proof-of-useful-work blockchain Open-source project, Pearl Research Labs

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. Verification Plan, R. Dean (2026). Original
14. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
15. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
16. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
17. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
18. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
19. Mechanisms to Verify International Agreements About AI Development, A. Scher & L. Thiergart (2025). Original
20. Proofs of Useful Work from Arbitrary Matrix Multiplication, I. Komargodski & O. Weinstein (2025). Original
21. Pearl Floating Point Scheme Specification, Pearl Research Team (2026). Original
22. pearl: Monorepo for the Pearl network, Pearl Research Labs (2026). Original