Proposal Explorer

Add claims to see which ones the mechanisms address.

In production

• R3 Model identity attestation for showing users that a service runs the declared model weights
• R3 TEE remote attestation for AI workloads for showing which software ran to a party that distrusts the operator holding the hardware

No new hardware needed

Model identity attestation and TEE remote attestation for AI workloads

Flaws since mitigated

• Launch-state attestation does not by itself cover weights loaded later in Model identity attestation ^{3 15}
• Software-only forgery of SEV-SNP attestation (RMPocalypse, Fabricked) in TEE remote attestation for AI workloads ^{13 14 24 25}

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

• Side-channel suppression for isolated facilities, RAND secure inference data center (SIDC) design: Analysis
• Model identity attestation: Independent red-team
• TEE remote attestation for AI workloads: Independent red-team

Open critical flaws

• Underlying attestation can be forged or relayed in Model identity attestation

  Critical for the enclave route against an operator with physical access to affected hardware, or control of an unpatched SEV-SNP hypervisor. It does not apply to the recomputation route. 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. ^{4 6 10 12 13 14}

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

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

  Related mechanism R1 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 flaw is mitigated. Add

• DDR5 memory-bus interposers forge Intel TDX attestations and break SEV-SNP protections (TEE.fail, DDRop) in TEE remote attestation for AI workloads

  Critical when the verifier must resist physical access plus host control on the affected DDR5 platforms. The Intel demonstrations defeat attestation; TEE.fail's AMD demonstration extracts a guest key, not an AMD attestation key. These results do not cover every TEE architecture.

  Independent researchers placed an interposer, built for under $1000, on the DDR5 memory bus of servers running Intel TDX and AMD SEV-SNP. Server TEEs encrypt memory deterministically, without integrity or freshness protection, and the researchers exploited this to recover secrets. The attack needs physical access and root privileges.

  • On Intel, they extracted the provisioning certification key from a machine that Intel's service rated fully up to date. This per-CPU key signs the keys used in SGX and TDX attestation. With it they forged SGX and TDX attestations.
  • On AMD SEV-SNP with ciphertext hiding enabled, they recovered an ECDSA private key used by OpenSSL inside the virtual machine. It was not an AMD attestation key. Other independent attacks did break SEV-SNP attestation. Battering RAM did so with a DDR4 interposer, and RMPocalypse and Fabricked from malicious host software.

  A second team, from KU Leuven, ETH Zurich, Durham University and Google, built DDRop, an active DDR5 interposer with a bill of materials of $159. It silently drops memory writes, which memory encryption without freshness protection cannot detect. With brief physical access and control of the host software and BIOS, the researchers forced trust domains into debug mode and forged attestation reports on an up-to-date Intel TDX platform. The same primitive breaks the integrity of Scalable SGX and SEV-SNP, though the authors report no SEV-SNP attestation forgery.

  The TEE.fail authors report that Intel and AMD consider interposer attacks out of scope, which leaves physical security as the only mitigation. The DDRop authors report the same position, and that both vendors issued security advisories on disclosure in September 2026. PAL*M lists this attack class as out of its scope, and Tinfoil's documentation acknowledges it. Gloria Z calls key extraction through bus interposition "relatively low-hanging fruit" in an international treaty scenario. ^{4 6 10 12 13 15 23 24}

  Demonstrated attack · Critical · Open · Mechanism-class evidence. On the record

  Related mechanism R1 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 flaw is mitigated. Add

• DDR4 memory-bus interposers forge SGX and SEV-SNP attestation (Battering RAM, WireTap) in TEE remote attestation for AI workloads

  Critical for the tested DDR4 SGX and SEV-SNP configurations against a physical host attacker. The authors exclude DDR5 from these demonstrations, including TDX servers; the DDR5 attacks have a separate finding.

  Two independent teams broke server TEE attestation on DDR4 memory with interposers they built themselves. Both attacks need physical access to install the device and root privileges on the host.

  • Battering RAM, by researchers at KU Leuven and the Universities of Birmingham and Durham, uses an interposer with a bill of materials of $47.62. It creates memory aliases at runtime, which bypasses the boot-time alias checks that AMD and Intel introduced against static aliasing attacks such as BadRAM. On Intel Scalable SGX it gained arbitrary read and write access to enclave plaintext and extracted SGX's platform provisioning key, which lets an attacker forge attestation certificates for arbitrary quoting enclaves. On up-to-date AMD SEV-SNP servers it captured the launch digests of genuine VMs and replayed them into modified VMs, so that backdoored VMs pass attestation.
  • WireTap, by researchers at Purdue University and Georgia Tech, uses an interposer built for under $1000 that records DDR4 bus traffic. On a Xeon Scalable server in fully trusted status it recovered the ECDSA attestation key of SGX's Quoting Enclave in 45 minutes and forged SGX quotes. The authors then showed end-to-end attacks on SGX-based blockchain deployments.

  Both attacks are limited to DDR4 systems. The Battering RAM authors state that all commercial TDX machines use DDR5, and the WireTap authors state that 4th and 5th generation Xeon Scalable processors need DDR5 and are not affected by their current work. According to the Battering RAM authors, Intel and AMD acknowledged the findings but consider physical attacks on DRAM out of scope for their current products. The WireTap authors report that Intel considers their attack outside the SGX threat model, and that there is no mitigation besides running servers in secure physical environments. ^{12 20}

  Demonstrated attack · Critical · Open · Mechanism-class evidence. On the record

  Related mechanism R1 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 flaw is mitigated. Add

Family findings

• Side-channel suppression for isolated facilities

  Context for RAND secure inference data center (SIDC) design. These findings concern the family or other implementations; applicability must be checked against their stated scope.

  • 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. ²

    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. ²

    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. ²

    Open question · Significant · Open. On the record

Open significant flaws

8 flaws in 3 mechanisms

• Everything rests on the trusted setup in RAND secure inference data center (SIDC) design

  Reference measurements for model weights and reference data are established in a trusted setup phase. The report states that the system cannot detect compromise that happened before ingestion if the trusted setup itself is compromised. ¹

  Theoretical argument · Significant · Open. On the record

• For private models, a user can confirm consistency but not content in Model identity attestation

  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. ^{3 16}

  Open question · Significant · Open. On the record

• Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel in Model identity attestation

  The recomputation variant assumes that every input, output and seed is logged correctly, and that the attacker can neither predict nor manipulate which messages are sampled for verification. Legitimate nondeterminism concentrates at a few token positions, and slow leaks within the tolerated slack remain possible. An independent study showed that an adversary who controls the prompts roughly doubles the bits leaked per token, reducing the exfiltration slowdown from 146–254 times under benign prompts to 60–118 times. The attack targets the exfiltration bound, not the check that outputs match the declared model. ^{5 11}

  Demonstrated attack · Significant · Open. On the record

  Related mechanism R1 Network taps and certifiers: Taps are proposed to copy and hash traffic on the monitored links, reducing reliance on the prover's own log. This still depends on the monitored boundary and trusted capture. A pointer, not evidence that this flaw is mitigated. Add

  Related mechanism R3 Deterministic and bit-exact inference: Bit-exact inference would remove the numerical tolerance that leaves this channel. A pointer, not evidence that this flaw is mitigated. Add

• H100 attestation not bound to a specific confidential VM in TEE remote attestation for AI workloads

  The demonstration combines a genuine H100 report with forged Intel TDX evidence. It depends on the CPU attestation already being defeated; a GPU report alone does not demonstrate that an intact CPU-to-GPU trust chain was bypassed.

  The TEE.fail authors fetched genuine H100 confidential-computing attestations from a rented server running their TDX VM. They combined these with forged TDX quotes. A proxy running outside any TEE then passed both the TDX and the GPU attestation checks. The authors attribute this to NVIDIA not binding the H100 to the identities of specific VMs. Their site states more generally that NVIDIA's attestation reports are not bound to a specific confidential VM or CPU. Intel, AMD, NVIDIA and the affected deployments acknowledged the findings, according to the authors, and the affected deployments were working on mitigations. The attack does not target NVIDIA's confidential-computing components directly, so the authors state that there are no mitigations on the NVIDIA side. ¹⁰

  Demonstrated attack · Significant · Open · Mechanism-class evidence. On the record

• Side channels and other attacks by the host on CPU and GPU TEEs in TEE remote attestation for AI workloads

  The cited studies concern particular CPU and GPU platforms and attack prerequisites. StackWarp has AMD microcode patches; the open class-level entry does not mean every cited defect is unmitigated or applies to every TEE-backed implementation.

  PAL*M and Attestable Audits cite published side-channel, single-stepping, interrupt-injection and memory-aliasing attacks on Intel TDX and AMD SEV, including T-Time, TDXploit, CIPHER-LEAKS, Heckler and BadRAM. PAL*M treats them as out of scope. Attestable Audits proposes revoking vulnerable enclave images. Gloria Z notes that performance counters have themselves been used as a side channel, for example in CounterSEVeillance. New attacks of this kind continue to appear. In StackWarp, researchers at CISPA showed that a malicious hypervisor can shift the stack pointer of an SEV-SNP guest on AMD Zen 1 to Zen 5 processors with simultaneous multithreading enabled, which fully breaks the guest's integrity. AMD released microcode patches. On the GPU side, an independent analysis of NVIDIA's confidential computing by IBM Research and Ohio State University found that bulk command and data transfers are protected, but some metadata, timing behaviour and coordination signals remain in unprotected shared memory. The authors report that these can reveal computational behaviour and in some cases allow manipulation of operations. They disclosed the findings to NVIDIA. ^{4 15 16 26 27}

  Demonstrated attack · Significant · Open · Mechanism-class evidence. On the record

• Attestation covers launch state, and measurements can be incomplete in TEE remote attestation for AI workloads

  A general measurement-boundary limitation. The concrete WhatsApp configuration findings were fixed before launch; Apple's research-environment configuration flaw was also fixed. Their fixes do not remove the need to bind each deployment's runtime inputs.

  Attestation measures launch state, not runtime state. Data loaded later, such as model weights, must be bound separately. Gloria Z argues that gaps in measuring feature flags, environment variables and invocation arguments are "perhaps the most likely failure mode". She also warns that a badly designed hashing scheme could let two models with significantly different properties share a hash "without breaking the hash function itself". Independent reviews of production systems have found such gaps. In WhatsApp's deployment, Trail of Bits found environment variables and ACPI tables loaded outside the measurement, and rated both high severity. Meta fixed them. On an Apple PCC node running in Apple's research environment, a researcher reports that tampered configuration files left the attestation unchanged. ^{3 15 21 22 28}

  Theoretical argument · Significant · Open · Mechanism-class evidence. On the record

• Deployment-level attestation does not cover the whole chip in TEE remote attestation for AI workloads

  A limitation of deployment-level evidence when the claim concerns all activity on a chip. It does not defeat a narrower claim about which software served one attested request.

  An attestation shows what one confidential VM runs. It does not show what else the hypervisor runs on the same hardware. Gloria Z calls the difference between deployment-level attestation and chip-wide monitoring "the gaping hole in this plan". This matters most for negative claims such as the absence of training. ¹⁵

  Theoretical argument · Significant · Open · Mechanism-class evidence. On the record

  Related mechanism R2 On-chip telemetry from timing, memory and performance counters: On-chip counters are a proposed route to evidence about everything a chip runs, which attestation of one workload does not give. A pointer, not evidence that this flaw is mitigated. Add

• Root of trust concentrated in a few hardware vendors in TEE remote attestation for AI workloads

  Vendor trust is an assumption of the attestation chain. The root-seed extraction study concerns AMD EPYC Milan and firmware downgrade with privileged host and platform-flash access; it is not evidence of the same failure on Intel, NVIDIA or all AMD generations.

  The root of trust is the certificate authorities of a small number of vendors (AMD, Intel and NVIDIA), which generate the keys and fuse them onto the chips. Gloria Z notes that whoever has access to a hardware key, or can certify one, can in principle produce valid reports for arbitrary measurements without the physical chip. Attestable Audits notes that the approach holds only "as long as the vendor of the secure hardware is trusted". A 2026 preprint reports that a host with root control and the ability to rewrite platform flash can downgrade an AMD EPYC Milan processor to legacy security-processor firmware and extract the hardware root seed from which SEV-SNP attestation keys are derived. The authors state that this lets them forge attestation reports for any firmware version. AMD describes the firmware-loader flaw the attack starts from as a legacy attack mitigated in 2021. ^{15 16 29 30}

  Theoretical argument · Significant · Open · Mechanism-class evidence. On the record

Open minor flaws

1 mechanism with minor findings

• Security weakens over long operation in RAND secure inference data center (SIDC) design

  The authors claim that the facility can withstand attacks at the OC5 level for a five-year operational period. They expect its ability to withstand long OC5 campaigns to become less robust the longer the facility remains in operation. ¹

  Theoretical argument · Minor · Open. On the record

Not yet demonstrated

R1 Side-channel suppression for isolated facilities

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

• R1 Hardware-enabled guarantees (flexHEG) and guarantee processors Add
  • Bears on the open critical flaw “Underlying attestation can be forged or relayed” in Model identity attestation. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
  • Bears on the open critical flaw “DDR5 memory-bus interposers forge Intel TDX attestations and break SEV-SNP protections (TEE.fail, DDRop)” in TEE remote attestation for AI workloads. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
  • Bears on the open critical flaw “DDR4 memory-bus interposers forge SGX and SEV-SNP attestation (Battering RAM, WireTap)” in TEE remote attestation for AI workloads. A tamper-protected enclosure around the chip is the proposed answer when the party that holds the hardware may attack it physically.
  • TEE remote attestation for AI workloads waits on it. Vendor threat models exclude sophisticated physical attacks, but in international verification the prover holds the hardware.
• R3 Deterministic and bit-exact inference Add
  • Bears on the open significant flaw “Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel” in Model identity attestation. Bit-exact inference would remove the numerical tolerance that leaves this channel.
  • Model identity attestation waits on it. Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling.
• R2 On-chip telemetry from timing, memory and performance counters Add
  • Bears on the open significant flaw “Deployment-level attestation does not cover the whole chip” in TEE remote attestation for AI workloads. On-chip counters are a proposed route to evidence about everything a chip runs, which attestation of one workload does not give.
  • TEE remote attestation for AI workloads waits on it. Negative claims such as "no undeclared training" need chip-wide accounting of all workloads, which attestation does not provide.
• R1 Network taps and certifiers Add
  • Bears on the open significant flaw “Recomputation depends on trusted logging and randomness, and its tolerance leaves a covert channel” in Model identity attestation. Taps are proposed to copy and hash traffic on the monitored links, reducing reliance on the prover's own log. This still depends on the monitored boundary and trusted capture.

Blockers

12 blockers recorded

• Side-channel suppression for isolated facilities
  • No prototype exists; RAND recommends prototyping key security features and integration now. Adversarial validation ¹
  • The report describes internal integrity checks, audit logging and accreditation, but no way for a party outside the operator to verify the facility's properties. Access & governance ¹
  • Human review of every prompt and response makes each request take three to five minutes, with the review steps as the rate-limiting factor. Performance & compatibility ¹
  • Detailed design information is withheld from the public report and is to be evaluated privately with stakeholders, which limits independent public scrutiny. Access & governance ¹
• Model identity attestation
  • Attestation that resists physical attackers, for the enclave variant. Hardware trust. Waits on TEE remote attestation for AI workloads ¹⁰
  • Numerical nondeterminism limits how tightly recomputation can pin down the model and sampling. Protocol soundness. Waits on Deterministic and bit-exact inference ⁵
  • The recomputation variant needs the verifier to hold the declared weights. Access & governance ⁵
• TEE remote attestation for AI workloads
  • Vendor threat models exclude sophisticated physical attacks, but in international verification the prover holds the hardware. Hardware trust. Waits on Hardware-enabled guarantees (flexHEG) and guarantee processors ^{10 12 17 20 23 31}
  • Negative claims such as "no undeclared training" need chip-wide accounting of all workloads, which attestation does not provide. Coverage & hidden compute. Waits on On-chip telemetry from timing, memory and performance counters ¹⁵
  • Multi-GPU and multi-node coverage is incomplete, because Hopper leaves NVLink traffic unencrypted and NVIDIA's April 2026 release notes list no multi-node confidential mode. Performance & compatibility ^{17 32}
  • Rival parties have not agreed on trust roots and key provenance they would accept. Access & governance ¹⁵
  • CPU-only enclaves are costly for large models, because in the Attestable Audits prototype CPU inference cost 21.7 times as much per token as GPU inference and the enclave roughly doubled the CPU cost. Performance & compatibility ¹⁶

From the family or selected implementation's record. ?

Model weights

Depends on the design for Model identity attestation.

Hidden by TEE remote attestation for AI workloads.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

Inputs and outputs

Depends on the design for Model identity attestation.

Hidden by TEE remote attestation for AI workloads.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

Training data

Hidden by TEE remote attestation for AI workloads.

Not involved: Model identity attestation.

Unspecified for Side-channel suppression for isolated facilities. Check the implementation record.

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

Model identity attestation

• R2 Attestable Audits Research prototype, University of Cambridge
• R2 PAL*M Research prototype, University of Waterloo
• R3 Tinfoil model identity (Modelwrap) Product, Tinfoil

TEE remote attestation for AI workloads

• R3 Apple Private Cloud Compute Product
• R2 Attestable Audits Research prototype, University of Cambridge
• R2 Cove Open-source project
• R2 PAL*M Research prototype, University of Waterloo
• R3 Tinfoil model identity (Modelwrap) Product, Tinfoil

1. Highly Secure Inference Data Centers: A Vertically Integrated Strategy for Security Engineering, S. F. Comer et al. (2026). Original
2. Suppressing Side Channels in an Untrusted Data Center via Retrofitted Defenses, N. Cankaya (2026). Original
3. How Tinfoil Proves Exactly What Model Is Running, Tinfoil Team (2026). Original
4. PAL*M: Property Attestation for Large Generative Models, P. Chantasantitam et al. (2026). Original
5. Verifying LLM Inference to Detect Model Weight Exfiltration, R. Rinberg et al. (2025). Original
6. A primer on secure enclaves, Tinfoil (2026). Original
7. Backend infrastructure, Tinfoil (2026). Original
8. How verification works in Tinfoil, Tinfoil (2026). Original
9. modelwrap: Reproducible dm-verity read-only image of Huggingface models, Tinfoil (2026). Original
10. TEE.fail: Breaking Trusted Execution Environments via DDR5 Memory Bus Interposition, J. Chuang et al. (2026). Original
11. Adversarial Entropy Inflation Against Gumbel-Based Inference Verification, N. Kezins (2026). Original
12. Battering RAM: Low-Cost Interposer Attacks on Confidential Computing via Dynamic Memory Aliasing, J. De Meulemeester et al. (2026). Original
13. RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP, B. Schlüter & S. Shinde (2025). Original
14. SEV-SNP RMP Initialization Vulnerability (AMD-SB-3020), AMD (2025). Original
15. On TEEs for Privacy-Preserving Monitoring in AI Governance, Gloria Z (2026). Original
16. Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments, C. Schnabl et al. (2025). Original
17. NVIDIA Secure AI with Blackwell and Hopper GPUs (White Paper), NVIDIA (2025). Original
18. Now in General Availability: NVIDIA H100 GPUs in Microsoft Azure Confidential Virtual Machines, C. Su (2024). Original
19. Private Cloud Compute: A new frontier for AI privacy in the cloud, Apple Security Engineering and Architecture (SEAR) (2024). Original
20. WireTap: Breaking Server SGX via DRAM Bus Interposition, A. Seto et al. (2025). Original
21. What we learned about TEE security from auditing WhatsApp's Private Inference, Trail of Bits (2026). Original
22. Meta WhatsApp Private Processing (security review), Trail of Bits (2025). Original
23. DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 Writes, J. De Meulemeester et al. (2026). Original
24. Fabricked: Misconfiguring Infinity Fabric to Break AMD SEV-SNP, B. Schlüter et al. (2026). Original
25. SEV-SNP Routing Misconfiguration (AMD-SB-3034), AMD (2026). Original
26. Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing, Z. Gu et al. (2026). Original
27. StackWarp: Breaking AMD SEV-SNP Integrity via Deterministic Stack-Pointer Manipulation through the CPU's Stack Engine, R. Zhang et al. (2026). Original
28. Beyond Prompt Injection: Hacking Apple's Private Cloud Compute, D. Selmanaj (2026). Original
29. Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan via a Software-Only Attack, M. Shen & Y. Qin (2026). Original
30. MilanLaunchy Firmware Loader (AMD-SB-3045), AMD (2026). Original
31. Technical Options for Flexible Hardware-Enabled Guarantees, J. Petrie & O. Aarne (2025). Original
32. NVIDIA Trusted Computing Solutions Release Notes (R595 TRD1), NVIDIA (2026). Original