Proposal Explorer

Add claims to see which ones the mechanisms address.

Operational use

• Operational use Hardware-attested weight binding for hardware-attested weight binding showing users that a service runs its committed weights
• Operational use 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

Hardware-attested weight binding, TEE remote attestation for AI workloads and On-chip telemetry from timing, memory and performance counters

Failures since mitigated

• Launch-state attestation does not by itself cover weights loaded later in Hardware-attested weight binding ^{1 11}
• Software-only forgery of SEV-SNP attestation (RMPocalypse, Fabricked) in TEE remote attestation for AI workloads ^{9 10 20 21}

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.

• Hardware-attested weight binding: Independent red-team
• TEE remote attestation for AI workloads: Independent red-team
• On-chip telemetry from timing, memory and performance counters: Red-teamed

Open critical failures

• 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. ^{2 3 7 8 9 10}

  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

• 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. ^{2 3 7 8 9 11 19 20}

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

  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

• 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. ^{8 16}

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

  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

Open significant failures

5 failures in 2 mechanisms

• 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. ⁷

  Known failure · 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. ^{2 11 12 22 23}

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

• 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. ^{11 12 25 26}

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

• Adversarially disguised fine-tuning partly evades classification in On-chip telemetry from timing, memory and performance counters

  Across 20 evasion strategy families in five monitor-evader rounds, the classifier's accuracy against the most challenging disguised workloads held out from training was 43–87%. White-box LoRA fine-tuning was the only evasion family detected less than half the time. The evaluation covered single nodes, PyTorch-level evasion and NVIDIA hardware. ²⁹

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

• Counters leak information about protected workloads in On-chip telemetry from timing, memory and performance counters

  Performance counters have been used as a side channel against TEEs, for example in CounterSEVeillance. NVIDIA disables performance counters in full confidential-computing mode, stating that they could provide an avenue for side-channel attacks. Richer counters for verification therefore pull against confidentiality. ^{11 13}

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

Scope limitations

• 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. ^{1 12}

  Scope limitation · Open question. 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. ^{1 11 17 18 24}

  Scope limitation · Theoretical argument · 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. ¹¹

  Scope limitation · Theoretical argument · Mechanism-class evidence. On the record

  Related mechanism Research demo 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 failure is mitigated. In the proposal.

• Software-read telemetry can be forged by the operator in On-chip telemetry from timing, memory and performance counters

  NVML-based classification assumes trustworthy telemetry. Without a tamper-resistant read path, an authenticated telemetry channel and secure boot of the monitoring software, an operator who controls the full software stack could forge counter values. Monfared et al. start from the same premise: current GPUs expose little trusted telemetry and can be modified or virtualized. ^{27 29}

  Scope limitation · Theoretical argument. On the record

  Related mechanism Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors: A guarantee processor on the chip would give the tamper-resistant, authenticated telemetry path the flaw says is missing. A pointer, not evidence that this failure is mitigated. Add

• Timing challenges do not identify the individual chip in On-chip telemetry from timing, memory and performance counters

  GEMM and VDF challenges can be answered by identical GPUs elsewhere, and floating-point fingerprints distinguish GPU models, not individual devices. GPU virtualization adds timing leakage that prevents attributing compute use. ²⁷

  Scope limitation · Theoretical argument. On the record

Open questions

• No quantified error rates or formal thresholds for timing primitives in On-chip telemetry from timing, memory and performance counters

  Monfared et al. state that false-positive and false-negative rates are not quantified and leave hardware-specific formal thresholds to future work. ²⁷

  Open question · Open question. On the record

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

• Proposed Hardware-enabled guarantees (flexHEG) and guarantee processors Add
  • Bears on the open critical failure “Underlying attestation can be forged or relayed” in Hardware-attested weight binding. 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 failure “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 failure “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.
  • On-chip telemetry from timing, memory and performance counters waits on it. Shipping accelerators need a tamper-resistant, authenticated telemetry path.

Shared foundations

• TEE remote attestation for AI workloads relied on by Hardware-attested weight binding and On-chip telemetry from timing, memory and performance counters. In the proposal
• Hardware-enabled guarantees (flexHEG) and guarantee processors relied on by TEE remote attestation for AI workloads and On-chip telemetry from timing, memory and performance counters

Blockers

10 blockers recorded

• Hardware-attested weight binding
  • Attestation that resists physical attackers, for the enclave variant. Hardware trust. Waits on TEE remote attestation for AI workloads ⁷
• 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 ^{7 8 13 16 19 30}
  • 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 ¹¹
  • 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 ^{13 31}
  • Rival parties have not agreed on trust roots and key provenance they would accept. Access & governance ¹¹
  • 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 ¹²
• On-chip telemetry from timing, memory and performance counters
  • Shipping accelerators need a tamper-resistant, authenticated telemetry path. Hardware trust. Waits on Hardware-enabled guarantees (flexHEG) and guarantee processors ^{28 29}
  • NVIDIA's full confidential-computing mode disables the hardware performance counters its profiling tools use, so telemetry that needs them conflicts with it. Privacy & leakage ^{11 13}
  • Continuous challenge puzzles cost power and throughput on production workloads. Performance & compatibility ²⁷
  • Evaluation has not gone beyond single nodes, framework-level evasion and one vendor's hardware. Adversarial validation ²⁹

From the family or selected implementation's record. ?

Model weights

Depends on the design for On-chip telemetry from timing, memory and performance counters.

Hidden by Hardware-attested weight binding and TEE remote attestation for AI workloads.

Inputs and outputs

Depends on the design for On-chip telemetry from timing, memory and performance counters.

Hidden by TEE remote attestation for AI workloads.

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

Training data

Depends on the design for On-chip telemetry from timing, memory and performance counters.

Hidden by TEE remote attestation for AI workloads.

Not involved: Hardware-attested weight binding.

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

TEE remote attestation for AI workloads

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

On-chip telemetry from timing, memory and performance counters

None on the map

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