Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Sampled inference recomputation and Memory wiping and proofs of secure erasure

No new hardware needed

Sampled inference recomputation and Memory wiping and proofs of secure erasure

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.

• Sampled inference recomputation, DiFR (Divergence From Reference): Analysis
• Memory wiping and proofs of secure erasure: Analysis

Family findings

• Sampled inference recomputation

  Context for DiFR (Divergence From Reference). 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.

  • 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 7 9}

    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

  • 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 10}

    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

  • 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. ^{1 11}

    Known failure · 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. ¹

    Known failure · Open question · Minor · Open. On the record

Open significant failures

2 failures in 2 mechanisms

• Statistical tolerance leaves a covert channel in DiFR (Divergence From Reference)

  Statistical schemes can put an upper bound on an adversary's covert bandwidth, but cannot close it. In the companion exfiltration study, the detector cut exfiltratable information to under 0.5% under benign prompt traffic. It did not cut it to zero. Its authors called the channel's size under adversarial prompts an open empirical question. An independent study attacked that detector, which uses the same Gumbel-margin statistic. An adversary who controls the prompts roughly doubled the bits leaked per token. Across six models, this cut the slowdown from 146–254 times under benign prompts to 60–118 times. The attack widens the exfiltration bound. It does not target DiFR's check that outputs match the declared configuration. ^{2 7 9}

  Known failure · Demonstrated attack · Significant · Open. On the record

• Outside help during challenges in Memory wiping and proofs of secure erasure

  Classic proofs of secure erasure assume the device is isolated during the protocol. Bursuc et al. relax this to a bound on how close a helper can be, enforced by round-trip times. In data centres, remote memory access has round trips of about 1–2 µs, against about 70–200 ns for local DRAM. The MIRI overview therefore says verification depends on ruling out RDMA by latency or physical disconnection. ^{14 15}

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

  Related mechanism Research demo Timed challenge-response and memory-occupation challenges: Timed challenges bound how far away a helper can be by how quickly it must answer. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Research demo Bandwidth limits and compartmentalization: Removing or capping links between groups of accelerators limits remote memory access during a challenge. A pointer, not evidence that this failure is mitigated. Add

Scope limitations

• Memory the wipe cannot reach in Memory wiping and proofs of secure erasure

  Amodo's inventory of a GB200 system lists many memory stores beyond GPU HBM and host DRAM. It notes that SSD controller DRAM sits on a private bus that host commands cannot read or write, and that its optimized algorithm leaves 25 GiB of HBM unattested. It also asks how switch memory could be wiped. ^{16 17}

  Scope limitation · Open question. On the record

• Gap between erased and total memory in Memory wiping and proofs of secure erasure

  Bursuc et al. note that memory left between the erased region and the device's full memory could hold data, and that their bounds are tighter only against a restricted adversary. ¹⁴

  Scope limitation · Theoretical argument. On the record

Open questions

• Speculative decoding and multi-model sampling not evaluated in DiFR (Divergence From Reference)

  The algorithms and experiments cover sampling from a single LLM. Speculative decoding was not evaluated. The authors sketch an extension to one speculative-decoding algorithm, without experiments. They note that other variants would need modified verification and extra metadata. ¹

  Open question · Open question. On the record

Open minor failures

1 mechanism with minor failures

• Mixed hardware widens the honest baseline in DiFR (Divergence From Reference)

  For Qwen3-30B-A3B, pooling honest runs across A100 and H200 GPUs and parallelism setups broadened the honest score distribution. Token-DiFR then failed 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 did. The authors report that matched provider and verifier environments, or pooling that weights rare large deviations, restore detection. ¹

  Known failure · Open question · Minor · Open. On the record

Not yet demonstrated

Proposed Memory wiping and proofs of secure erasure

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

• Research demo Bandwidth limits and compartmentalization Add
  • Bears on the open significant failure “Outside help during challenges” in Memory wiping and proofs of secure erasure. Removing or capping links between groups of accelerators limits remote memory access during a challenge.
• Research demo Timed challenge-response and memory-occupation challenges Add
  • Bears on the open significant failure “Outside help during challenges” in Memory wiping and proofs of secure erasure. Timed challenges bound how far away a helper can be by how quickly it must answer.
  • Memory wiping and proofs of secure erasure waits on it. Timed challenges must exclude remote memory and other helpers.

Missing prerequisites

• Research demo Timed challenge-response and memory-occupation challenges needed by Memory wiping and proofs of secure erasure Add

Blockers

6 blockers recorded

• Sampled inference recomputation
  • The verifier needs the model weights, so outsiders cannot use the method to verify providers of closed-weights models. Privacy & leakage ¹
  • The verifier must know and match the provider's sampling procedure, and in one prototype a sampling mismatch in a newer vLLM version produced large spurious logit differences. Performance & compatibility ^{1 4}
  • No independent red-team of DiFR's consistency check has been published, Amodo rates recomputation red-teaming 'not started', and the one independent attack study targets an exfiltration detector built on the same statistic. Adversarial validation ^{6 7}
• Memory wiping and proofs of secure erasure
  • Wipes take time: tens of minutes for a pod's volatile memory and hours for SSDs, displacing work. Performance & compatibility ^{15 16 17}
  • Timed challenges must exclude remote memory and other helpers. Coverage & hidden compute. Waits on Timed challenge-response and memory-occupation challenges ^{14 15}
  • All memory stores in a system must be inventoried and wiped at the same time. Coverage & hidden compute ¹⁶

From the family or selected implementation's record. ?

Model weights

Not involved: Memory wiping and proofs of secure erasure.

Unspecified for Sampled inference recomputation. Check the implementation record.

Inputs and outputs

Not involved: Memory wiping and proofs of secure erasure.

Unspecified for Sampled inference recomputation. Check the implementation record.

Training data

Not involved: Memory wiping and proofs of secure erasure.

Unspecified for Sampled inference recomputation. Check the implementation record.

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

Memory wiping and proofs of secure erasure

• 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

1. DiFR: Inference Verification Despite Nondeterminism, A. Karvonen et al. (2025). Original
2. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
3. adamkarvonen/difr (GitHub repository), A. Karvonen (2025). Original
4. Scaling Recomputation Inference Verification, Amodo Design (2026). Original
5. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
6. AI 2040 Plan A — Verification SITREP, Amodo Design (2026). Original
7. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
8. An Inference Verification Prototype — Stage 1, Amodo Design (2026). Original
9. Bit-Exact AI Inference Verification Without Performance Tradeoffs, N. Cankaya (2026). Original
10. Example Schemes for Verifying High-Stakes AI Agreements, Amodo Design (2026). Original
11. TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference, J. M. Ong et al. (2025). Original
12. Verification Plan, R. Dean (2026). Original
13. Secure Code Update for Embedded Devices via Proofs of Secure Erasure, D. Perito & G. Tsudik (2010). Original
14. Software-Based Memory Erasure with Relaxed Isolation Requirements, S. Bursuc et al. (2024). Original
15. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
16. Memory Wipes - Performance Analysis, Amodo Design (2026). Original
17. Improving Disk Wiping Speed for Memory Wipes, Amodo Design (2026). Original
18. Amodo-Design/PoSE-Memory-Wiping (GitHub repository), Amodo Design (2026). Original
19. Empirical Evaluation of Memory-Erasure Protocols, R. Gil-Pons et al. (2025). Original