Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Zero-knowledge proofs of inference

No new hardware needed

Zero-knowledge proofs of inference and Hardware-attested weight binding

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
• Hardware-attested weight binding, Attestable Audits: Analysis

Family findings

• Hardware-attested weight binding

  Context for Attestable Audits. Findings from the mechanism family appear here as context. They apply to an implementation only when its own record lists them, under the conditions stated there.

  • Underlying attestation can be forged or relayed in Hardware-attested weight binding

    Critical for weight binding against an operator with physical access to affected hardware, or with control of the hypervisor on an AMD SEV-SNP platform without AMD's fixes. PAL*M excludes physical attacks, and Tinfoil acknowledges this boundary.

    The enclave route inherits the platform-specific TEE attestation failures. Intel TDX forgery and H100 relay were demonstrated with physical access and host control. Battering RAM defeated AMD SEV-SNP attestation on DDR4 servers; RMPocalypse did so from malicious host software on platforms without AMD's fixes. These demonstrate failures of the trust roots, not of each model-commitment protocol. ^{15 16 17 18 19 20}

    Response: The TEE.fail authors report that physical interposer attacks are outside Intel's and AMD's threat models. AMD reports fixes for RMPocalypse.

    Known failure · Demonstrated attack · Critical · Open · Inherited finding. On the record · Related finding in TEE remote attestation for AI workloads

    Related mechanism Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors: A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically. A pointer, not evidence that this failure is mitigated. Add

  • Launch-state attestation does not by itself cover weights loaded later in Hardware-attested weight binding

    Attestation measures launch state, and weights are read from disk after boot. A signature checked at load time does not stop a malicious hypervisor from altering the disk afterwards. Tinfoil reports mitigating this with dm-verity checks on every read. Unmeasured runtime configuration remains a general risk. ^{21 22}

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

  • For private models, a user can confirm consistency but not content in Hardware-attested weight binding

    When weights are not published, users can check that the same root hash is served each time, but not what the model is. Pairing the hash with an attested evaluation, as in Attestable Audits, is one proposed remedy. ^{13 21}

    Scope limitation · Open question. 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

• Relies on the TEE vendor and inherits TEE attacks in Attestable Audits

  The prototype trusts AWS Nitro, not the Intel TDX or AMD SEV-SNP attestation roots targeted by the cited confidential-VM studies. Those studies are class context, not a demonstrated attack on this Nitro prototype.

  The design depends on trusting the TEE vendor, AWS in the prototype. The authors cite memory-aliasing, ciphertext side-channel and malicious-interrupt attacks on confidential VMs (BadRAM, CIPHERLEAKS, Heckler). Their answer is to revoke vulnerable base images once such attacks are discovered. ¹³

  Response: The authors propose revoking vulnerable base images; they do not report a red-team evaluation of the prototype.

  Scope limitation · Theoretical argument · Inherited finding. On the record · Related finding in TEE remote attestation for AI workloads

• CPU-only enclaves force small, quantized models and high cost in Attestable Audits

  Memory limits required 4-bit quantization, and the quantized model scored 51.4% on zero-shot MMLU. CPU inference cost 21.7 times as much per token as GPU inference, and the enclave roughly doubled the CPU cost. The authors wrote that H100 confidential computing had no multi-GPU support. NVIDIA's white paper of August 2025 describes a protected-PCIe mode that passes all eight GPUs of a Hopper HGX node to one confidential VM, with NVLink traffic unencrypted. ^{13 14}

  Scope limitation · Open question. On the record

Open questions

• Prompt-based model exfiltration is a residual gap in Attestable Audits

  The authors state that "prompt-based model exfiltration during the user interaction step remains a residual gap". ¹³

  Open question · Open question. On the record

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

• Operational use TEE remote attestation for AI workloads Add
  • Hardware-attested weight binding waits on it. The prototype needs porting to GPU confidential computing to handle larger models; the authors expect an overhead as small as 5 times there.
• 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.

Missing prerequisites

• Operational use TEE remote attestation for AI workloads needed by Hardware-attested weight binding Add

Blockers

6 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
• Hardware-attested weight binding
  • The prototype needs porting to GPU confidential computing to handle larger models; the authors expect an overhead as small as 5 times there. Performance & compatibility. Waits on TEE remote attestation for AI workloads ¹³
  • As of September 2026 no code has been released for the prototype. Adversarial validation ¹³

From the family or selected implementation's record. ?

Model weights

Hidden by Zero-knowledge proofs of inference.

Unspecified for Hardware-attested weight binding. Check the implementation record.

Inputs and outputs

Shown by Zero-knowledge proofs of inference.

Unspecified for Hardware-attested weight binding. Check the implementation record.

Training data

Not involved: Zero-knowledge proofs of inference.

Unspecified for Hardware-attested weight binding. Check the implementation record.

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

Hardware-attested weight binding

• Research demo Attestable Audits Research prototype, University of Cambridge
• Research demo PAL*M Research prototype, University of Waterloo
• Operational use Tinfoil model identity (Modelwrap) Product, Tinfoil

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. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
14. NVIDIA Secure AI with Blackwell and Hopper GPUs (White Paper), NVIDIA (2025). Original
15. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). Original
16. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). Original
17. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). Original
18. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). Original
19. A primer on secure enclaves, Tinfoil (2026). Original
20. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). Original
21. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original
22. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). Original