Proposal Explorer

Add claims to see which ones the mechanisms address.

Built for an adversarial prover

Bandwidth limits and compartmentalization and Network taps and certifiers

Failures since mitigated

• Verifier dictionary attacks on hashes in Network taps and certifiers ⁸

Not counted

Excluded by your filters: Hardware-enabled guarantees (flexHEG) and guarantee processors

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.

• Bandwidth limits and compartmentalization: Analysis
• Network taps and certifiers: Analysis
• Hardware-enabled guarantees (flexHEG) and guarantee processors: Analysis · excluded by filters

Excluded by your filters

• Hardware-enabled guarantees (flexHEG) and guarantee processors Needs changes to future chip designs; the filter allows existing chips only.

Open significant failures

7 failures in 3 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. ²

  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. ⁵

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

• Output nondeterminism leaves covert capacity in Network taps and certifiers

  Hashing cannot remove information hidden in the outputs themselves. The Secure Gateway Device paper estimates that about 0.1 bit per token remains even with seed-synchronized replay checks. For a 200k-GPU inference cluster at full load (2,000 tokens per GPU per second), that is about 40 Mbit/s of covert egress, enough to move a 1 TB model in under three days. The paper names this the core remaining challenge and points to deterministic replay or active scrubbing of hardware-induced entropy. An independent study found that an adversary who chooses the prompts roughly doubles the bits leaked per token under Gumbel-based inference verification; see Bounding unexplained information in outputs. ^{8 14}

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

  Related mechanism Operational use Deterministic and bit-exact inference: Deterministic replay is one of the two remedies the flaw's source names. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Research demo Bounding unexplained information in outputs: Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict. A pointer, not evidence that this failure is mitigated. Add

• Residual side channels in simple passive setups in Network taps and certifiers

  Amodo's analysis of its own tapped prototype lists unvalidated header fields, timing of permitted traffic and variation in response formatting as residual channels, and concludes that the passive tap must be replaced by an active one. ¹⁰

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

• State attackers can likely defeat current secure enclosures in Hardware-enabled guarantees (flexHEG) and guarantee processors

  The flexHEG authors write that "nation-state attackers can likely compromise the best current secure enclosures", and that the marginal cost of circumvention per device is hard to estimate. RAND similarly judges that anti-tamper measures "would not be insurmountable for a determined and well-resourced adversary", although they raise costs and can reveal tampering. ^{17 19}

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

• Firmware-only retrofits rely on Secure Boot, which fault injection can bypass in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Part II notes that the most common attack on Secure Boot replaces the firmware and applies a voltage glitch while the signature is being checked. It also notes that sophisticated actors may use microprobing or laser voltage probing to read key registers. ¹⁷

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

• FLOP accounting can be laundered through external data in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Results of earlier or parallel workloads could be hidden in the "external data" fed to a device, which would falsify the total FLOP count unless the inputs are explained or time delays are imposed. ¹⁷

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

Scope limitations

• 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. ²

  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. ²

  Scope limitation · Open question. On the record

• Some links cannot be passively tapped in Network taps and certifiers

  Cankaya notes that copper-connected scale-up domains (for example NVL72 racks and TPU v7 cubes) are much harder to tap than fibre, and that optical budgets make passive taps impractical on 400GBASE-SR8 multimode links. Amodo found no taps advertised for 53 GBaud links as of May 2026. ^{9 15}

  Scope limitation · Open question. On the record

• Encrypted fabrics hide plaintext from both parties in Network taps and certifiers

  Cankaya notes that with TEE-protected sessions whose keys are ephemeral and managed inside the TEE, neither the operator nor the manufacturer can recover session keys after the session, so tapped traffic could not be opened for recomputation. For other encrypted fabrics, the operator can retain keys. ⁹

  Scope limitation · Open question. On the record

• Completeness rests on physical monitoring left out of scope in Network taps and certifiers

  The Secure Gateway Device paper assumes the facility is physically monitored, and states that the whole architecture depends on the device being the only communication channel. It names radio emanation, power-line signalling and thermal channels as covert channels beyond that scope. ⁸

  Scope limitation · Open question. On the record

  Related mechanism Proposed Side-channel suppression for isolated facilities: Addresses the radio, power-line and thermal channels that network-level designs leave out. A pointer, not evidence that this failure is mitigated. Add

• Many important rules cannot be checked on-chip in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Malicious intent "is not a technical property observable on-chip", and misuse depends on what is done with a computation's results. A guarantee processor cannot easily tell whether a network is the whole system or one expert in a mixture-of-experts system. Part III judges that a fully local ruleset "may not be entirely feasible" for the same reason. ^{16 18}

  Scope limitation · Theoretical argument. On the record

• Coverage stops at flexHEG-equipped chips in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Motivated actors will always be able to use some compute that is not flexHEG-equipped. Recalling existing consumer GPUs would likely be impractical, and reaching perfect coverage, or conclusively proving that no secret government data centres exist, would be "practically quite difficult". ^{16 18}

  Scope limitation · Open question. On the record

  Related mechanism Proposed Chip registries and manufacturing records: Accounts for which chips exist and who holds them. A pointer, not evidence that this failure is mitigated. Add

  Related mechanism Proposed Remote detection of data centres: Looks for undeclared facilities that hold other chips. 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. ^{2 6 7}

  Open question · Theoretical argument. On the record

• Supply-chain diversion and hidden backdoors in Hardware-enabled guarantees (flexHEG) and guarantee processors

  Components could be diverted before a guarantee processor is added, and backdoors could be introduced during design or manufacturing. Open-source designs and physical scans of randomly selected chips are proposed as countermeasures. Part III proposes international oversight of production and extensive testing of a random sample of finished devices. ^{17 18}

  Open question · Open question. On the record

  Related mechanism Proposed Chip registries and manufacturing records: Records each chip's identity and owner from the fab onwards, which bears on diversion before a guarantee processor is fitted. It does not address hidden backdoors. A pointer, not evidence that this failure is mitigated. Add

Not yet demonstrated

Proposed Network taps and certifiers and Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors

Need new chip designs

Hardware-enabled guarantees (flexHEG) and guarantee processors

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 “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Deterministic replay is one of the two remedies the flaw's source names.
  • Network taps and certifiers waits on it. Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove.
• Research demo Bounding unexplained information in outputs Add
  • Bears on the open significant failure “Output nondeterminism leaves covert capacity” in Network taps and certifiers. Bounds the hidden information outputs can carry by measuring what the declared computation fails to predict.
• 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.
  • Network taps and certifiers waits on it. Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them.
  • Hardware-enabled guarantees (flexHEG) and guarantee processors waits on it. State-level attackers who hold the hardware can likely compromise the best current secure enclosures.
• Proposed Chip registries and manufacturing records Add
  • Hardware-enabled guarantees (flexHEG) and guarantee processors waits on it. Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities.
• Proposed Side-channel suppression for isolated facilities Add
  • Network taps and certifiers waits on it. Radio, power-line and thermal channels are not addressed by network-level designs.
• Operational use Sampled inference recomputation Add
  • Network taps and certifiers depends on it.
• Operational use TEE remote attestation for AI workloads Add
  • Hardware-enabled guarantees (flexHEG) and guarantee processors depends on it.

Missing prerequisites

• Research demo Tamper evidence for verifier devices needed by Bandwidth limits and compartmentalization and Network taps and certifiers Add
• Operational use Sampled inference recomputation needed by Network taps and certifiers Add
• Operational use Deterministic and bit-exact inference needed by Network taps and certifiers Add
• Proposed Side-channel suppression for isolated facilities needed by Network taps and certifiers Add
• Operational use TEE remote attestation for AI workloads needed by Hardware-enabled guarantees (flexHEG) and guarantee processors Add
• Proposed Chip registries and manufacturing records needed by Hardware-enabled guarantees (flexHEG) and guarantee processors Add

Shared foundations

• Tamper evidence for verifier devices relied on by Bandwidth limits and compartmentalization, Network taps and certifiers and Hardware-enabled guarantees (flexHEG) and guarantee processors

Blockers

14 blockers recorded

• Bandwidth limits and compartmentalization
  • No cap that a verifier can check has been implemented or red-teamed. Adversarial validation ²
  • The verifier must know that all traffic leaving a pod crosses the capped, monitored links. Coverage & hidden compute. Waits on Network taps and certifiers ³
  • 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 ^{2 5}
  • Advances in low-communication training could shrink the margin that the cap enforces. Capacity bounds ^{2 6 7}
• Network taps and certifiers
  • No complete verification tap has been demonstrated at production frontend link rates, and on the tested CPU no hash algorithm reached line rate with minimum-size frames. Performance & compatibility ^{15 22}
  • Nondeterministic inference leaves covert capacity in outputs that hashing cannot remove. Evidence binding. Waits on Deterministic and bit-exact inference ⁸
  • Taps and gateway devices need tamper-evident housing and physical monitoring so that traffic cannot bypass them. Hardware trust. Waits on Tamper evidence for verifier devices ^{3 8}
  • Radio, power-line and thermal channels are not addressed by network-level designs. Coverage & hidden compute. Waits on Side-channel suppression for isolated facilities ⁸
  • Red-teaming by specialists is called for but has not been reported. Adversarial validation ⁸
• Hardware-enabled guarantees (flexHEG) and guarantee processors
  • Integrated flexHEG needs substantial help from the accelerator manufacturer, and the authors estimate 3.7–7.9 years, from when the manufacturer starts work, for such hardware to displace other accelerators in frontier development. Access & governance ¹⁷
  • State-level attackers who hold the hardware can likely compromise the best current secure enclosures. Hardware trust. Waits on Tamper evidence for verifier devices ^{17 19}
  • Rival states would need to trust the design and manufacture of guarantee processors and enclosures, for example through open design, redundant processors from each side or oversight of production. Hardware trust ^{16 18}
  • Restricting future rule updates would need a formal language for rules, which the authors judge most likely infeasible for early flexHEG versions. Protocol soundness ¹⁶
  • Governing all relevant chips depends on knowing where they are, through chip registries and detection of undeclared facilities. Coverage & hidden compute. Waits on Chip registries and manufacturing records ¹⁸

From the family or selected implementation's record. ?

Model weights

Depends on the design for Network taps and certifiers.

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Bandwidth limits and compartmentalization.

Inputs and outputs

Depends on the design for Network taps and certifiers.

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Bandwidth limits and compartmentalization.

Training data

Depends on the design for Network taps and certifiers.

Hidden by Hardware-enabled guarantees (flexHEG) and guarantee processors.

Not involved: Bandwidth limits and compartmentalization.

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

Network taps and certifiers

• 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
• Proposed SASH confidential network logger Research prototype, Singapore AI Safety Hub (SASH)

Hardware-enabled guarantees (flexHEG) and guarantee processors

None on the map

1. Verification Plan, R. Dean (2026). Original
2. Traffic Shaping for Workload Classification, Lucid Computing (2026). Original
3. A System Overview for Near-Term, Low-Trust AI Compute Verification, N. Cankaya (2026). Original
4. De-risking Interconnect Limits for AI Verification, A. Scher et al. (2026). Original
5. The Tray as a Bandwidth Boundary, Amodo Design (2026). Original
6. DiLoCo: Distributed Low-Communication Training of Language Models, A. Douillard et al. (2024). Original
7. Does Distributed Training Undermine Compute Governance?, R. Rahman (2026). Original
8. Fingerprinting All AI Cluster I/O Without Mutually Trusted Processors, N. Cankaya et al. (2026). Original
9. The Fundamentals and Feasibility of Secure Network Taps for Verifying AI Datacenter Use, N. Cankaya (2026). Original
10. Fitting a Network TAP to our Inference Verification Prototype, Amodo Design (2026). Original
11. Amodo-Design/Inference-Recomputation-Prototype (GitHub repository), Amodo Design (2026). Original
12. inference-verification: Inference Verification Prototype, Singapore AI Safety Hub (SASH) (2026). Original
13. Internationalising AI Verification, Singapore AI Safety Hub (SASH) (2026). Original
14. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
15. Network Tapping for AI Verification: A Technical Assessment, Amodo Design (2026). Original
16. Flexible Hardware-Enabled Guarantees for AI Compute, J. Petrie et al. (2025). Original
17. Technical Options for Flexible Hardware-Enabled Guarantees, J. Petrie & O. Aarne (2025). Original
18. International Security Applications of Flexible Hardware-Enabled Guarantees, O. Aarne & J. Petrie (2025). Original
19. Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090, G. Kulp et al. (2024). Original
20. Secure, Governable Chips: Using On-Chip Mechanisms to Manage National Security Risks from AI & Advanced Computing, O. Aarne et al. (2024). Original
21. Hardware-Enabled Mechanisms for Verifying Responsible AI Development, A. O'Gara et al. (2025). Original
22. Network Traffic Hashing, Amodo Design (2026). Original