Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Bounding unexplained information in outputs, Sampled inference recomputation and Side-channel suppression for isolated facilities

Published attempts to break a system, including those that found failures. Testing history does not show that open flaws are resolved.

• Bounding unexplained information in outputs: Independent red-team
• Sampled inference recomputation, Low-trust AI compute verification system overview: Analysis
• Side-channel suppression for isolated facilities: Analysis

Family findings

• Sampled inference recomputation

  Context for Low-trust AI compute verification system overview. These findings concern the family or other implementations; applicability must be checked against their stated scope.

  • 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. ^{2 3 7}

    Demonstrated attack · Significant · Open. On the record

    Related mechanism R3 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 flaw is mitigated. Add

  • 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. ^{2 8}

    Theoretical argument · Significant · Open. On the record

    Related mechanism R1 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 flaw 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. ^{9 10}

    Theoretical argument · Significant · Open. On the record

  • 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. ¹⁰

    Open question · Minor · Open. On the record

Open significant flaws

9 flaws in 3 mechanisms

• Prompt-controlled entropy inflation widens the covert channel in Bounding unexplained information in outputs

  Gumbel-based inference verification tolerates token choices that honest GPU nondeterminism could produce, and the size of that tolerated set grows with the model's output entropy. Kezins, an independent researcher, showed that an adversary who controls the prompt distribution can raise output entropy and roughly double the bits leaked per token. Across six models of 1 to 32 billion parameters, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. Kezins argues that architectures built on the same unexplained-information bound inherit this attack surface, and recommends calibrating tolerances against local token entropy rather than benign traffic. ^{2 3}

  Demonstrated attack · Significant · Open. On the record

  Related mechanism R3 Deterministic and bit-exact inference: Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata. A pointer, not evidence that this flaw is mitigated. Add

• Information the declared computation explains is not bounded in Bounding unexplained information in outputs

  The bound limits unexplained bits only. Outputs that the declared computation fully explains can still carry valuable information: a compression study notes that an adversary with inference access can extract more proprietary information per bit than naive transmission allows. ^{1 4}

  Theoretical argument · Significant · Open. On the record

• Channels other than checked outputs are outside the bound in Bounding unexplained information in outputs

  The inference-verification scheme treats side channels as out of scope. A low-trust system design argues that suppressing physical covert bandwidth below kilobits per second is much more achievable than aiming for zero, and that a malicious device can leak one bit of information by deliberately outputting a wrong result. ^{2 5}

  Theoretical argument · Significant · Open. On the record

  Related mechanism R1 Side-channel suppression for isolated facilities: Physical side channels need separate suppression, which is this mechanism's purpose. A pointer, not evidence that this flaw is mitigated. In the proposal.

• The facility-level design is untested in Bounding unexplained information in outputs

  The compute-verification architecture is described with protocol details, potential attacks and prototyping plans, but no prototype results have been published. ¹

  Open question · Significant · Open. On the record

• Mismatches cannot be attributed to cheating or error in Low-trust AI compute verification system overview

  A failed hash or replay does not show whether it came from an evasion attempt, a random bit flip or an evaluation error. The author notes that if detected anomalies can plausibly be waved off as malfunctions, deterrence becomes less effective, so the parties need an agreed escalation procedure that ends in attribution. ⁵

  Theoretical argument · Significant · Open. On the record

• Inspector agents may be manipulable in Low-trust AI compute verification system overview

  Automated compliance screening with LLM-based inspector agents must resist prompt-injection attacks. Adversarially trained systems might hide malicious actions with steganography, which makes backdoor detection an open problem. ⁵

  Open question · Significant · Open. On the record

• Supply-chain implants may evade inspection in Side-channel suppression for isolated facilities

  Cankaya identifies malicious hardware embedded deep in purchased components as a residual risk that visual inspection and disassembly may not catch. He notes that radiographic examination under high-security standards could mitigate it. ¹¹

  Theoretical argument · Significant · Open. On the record

• Openings for airflow, power and optics weaken shielding in Side-channel suppression for isolated facilities

  Cankaya notes that keeping attenuation high while passing high-power airflow, cabling and optical links adds complexity beyond existing shielded-enclosure specifications. ¹¹

  Theoretical argument · Significant · Open. On the record

• Inspection assumptions may not hold in Side-channel suppression for isolated facilities

  The design's statistical argument assumes that visual or disassembly inspection catches every flaw that is present in a sampled unit. Cankaya is unsure whether destructive teardowns are defence-dominant or offence-dominant. ¹¹

  Open question · Significant · Open. On the record

Open minor flaws

1 mechanism with minor findings

• Deliberate faults leak a bit each in Low-trust AI compute verification system overview

  A malicious device can leak one bit by deliberately outputting a wrong result, which blocks a disclosure when the cross-comparison fails. The design therefore needs a pre-agreed budget of tolerated faults. ⁵

  Theoretical argument · Minor · Open. On the record

Not yet demonstrated

R1 Sampled inference recomputation and R1 Side-channel suppression for isolated facilities

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

• R3 Deterministic and bit-exact inference Add
  • Bears on the open significant flaw “Prompt-controlled entropy inflation widens the covert channel” in Bounding unexplained information in outputs. Bit-exact replay would remove the tolerance for numerical noise that sets the size of this channel. The record notes that it needs full hardware and software metadata.
  • Bounding unexplained information in outputs waits on it. Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata.
  • Sampled inference recomputation waits on it. Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question.
• R2 Bandwidth limits and compartmentalization Add
  • Bounding unexplained information in outputs waits on it. The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound.
• R2 Tamper evidence for verifier devices Add
  • Sampled inference recomputation waits on it. Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging.
• R2 Timed challenge-response and memory-occupation challenges Add
  • Sampled inference recomputation waits on it. Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open.
• R1 Network taps and certifiers Add
  • Sampled inference recomputation waits on it. Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question.
  • Bounding unexplained information in outputs depends on it.

Missing prerequisites

• R2 Bandwidth limits and compartmentalization needed by Bounding unexplained information in outputs Add
• R1 Network taps and certifiers needed by Bounding unexplained information in outputs and Sampled inference recomputation Add
• R3 Deterministic and bit-exact inference needed by Sampled inference recomputation Add

Shared foundations

• Side-channel suppression for isolated facilities relied on by Bounding unexplained information in outputs and Sampled inference recomputation. In the proposal
• Network taps and certifiers relied on by Bounding unexplained information in outputs and Sampled inference recomputation
• Deterministic and bit-exact inference relied on by Bounding unexplained information in outputs and Sampled inference recomputation

Blockers

13 blockers recorded

• Bounding unexplained information in outputs
  • The prover's compute must be isolated so that all traffic passes through the verifier's interlock; any unmonitored path voids the bound. Coverage & hidden compute. Waits on Bandwidth limits and compartmentalization ¹
  • Physical side channels need separate suppression, and one design treats a low residual bandwidth, rather than zero, as the realistic target. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ^{2 5}
  • Tolerance for numerical nondeterminism sets the size of the residual channel; bit-exact replay would remove it but needs full hardware and software metadata. Protocol soundness. Waits on Deterministic and bit-exact inference ^{3 5}
  • Recomputation over confidential weights and inputs needs a protected setting: prover recomputation in a verifier-controlled enclosure, verifier recomputation in a prover-controlled enclosure, or zero-knowledge proofs. Privacy & leakage ¹
  • No prototype of the facility-level architecture exists to red-team. Adversarial validation ¹
• Sampled inference recomputation
  • Empirical feasibility of passive optical splitting at 53–112 GBaud under realistic conditions is an open question. Performance & compatibility. Waits on Network taps and certifiers ⁵
  • Exact replay needs complete hardware and software metadata, and the tolerable slowdown from emulation is an open question. Performance & compatibility. Waits on Deterministic and bit-exact inference ⁵
  • Tamper-evident, rapidly mass-manufacturable and retrofittable enclosures for side-channel defence are an open research question, and physical security against covert communication in every monitored data centre is challenging. Hardware trust. Waits on Tamper evidence for verifier devices ⁵
  • A mass-manufacturable, good-enough side-channel defence, particularly power-line filtering, has not been constructed or red-teamed. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ⁵
  • Distinguishing one server's DRAM contents from another's by challenge-response timing, and a general challenge-response protocol for diverse data types, are open. Coverage & hidden compute. Waits on Timed challenge-response and memory-occupation challenges ⁵
  • The threat model is under-developed and needs input from cybersecurity and AI threat-modelling experts. Adversarial validation ⁵
• Side-channel suppression for isolated facilities
  • No prototype or red-team exists; the design is a first-pass viability study. Adversarial validation ¹¹
  • Volume costs of TEMPEST-grade power-line filters are uncertain, because existing products are mostly made to order. Performance & compatibility ¹¹

From the family or selected implementation's record. ?

Model weights

Depends on the design for Bounding unexplained information in outputs.

Not involved: Side-channel suppression for isolated facilities.

Unspecified for Sampled inference recomputation. Check the implementation record.

Inputs and outputs

Depends on the design for Bounding unexplained information in outputs.

Not involved: Side-channel suppression for isolated facilities.

Unspecified for Sampled inference recomputation. Check the implementation record.

Training data

Not involved: Bounding unexplained information in outputs and Side-channel suppression for isolated facilities.

Unspecified for Sampled inference recomputation. Check the implementation record.

Bounding unexplained information in outputs

None on the map

Sampled inference recomputation

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R2 DiFR (Divergence From Reference) Research prototype
• R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• R1 SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)
• R3 TOPLOC Open-source project, Prime Intellect

Side-channel suppression for isolated facilities

• R1 AI 2040 inference-only verification stack Proposed architecture, AI Futures Project
• R1 Low-trust AI compute verification system overview Proposed architecture, Machine Intelligence Research Institute
• R1 RAND secure inference data center (SIDC) design Proposed architecture, RAND

1. Verifying AI Compute by Bounding Unexplained Information Exfiltration, J. Petrie & Y. Mühlhäuser (2026). Original
2. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
3. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
4. Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains, R. Rinberg et al. (2026). Original
5. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
6. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
7. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
8. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
9. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
10. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
11. Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses, N. Cankaya (2026). Original