Google unveils TPU 8tx and TPU 8i Max for AI workloads
TPU 8tx, designed with AMD, targets confidential training and inference; TPU 8i Max doubles memory in one package.
Stories per day · 30 days
1 RSS
Relatedgoogle-cloud3ai-chips2azure2google2intel-sgx2nvidia2secure-enclaves2tee2tpu2a5x1accountable-disclosure1amd1amd-sev1anthropic1attestation1aws1bare-metal1confidential-ai1
19 stories, newest first · one card per story
Stories tagged #confidential-computing
Pilot evaluates Gemini 2.5 Flash Lite without sharing prompts or weights
PySyft and an NVIDIA H100 enclave on Google Cloud ran private AILuminate prompts against the model.
CORDE enforces accountable disclosure in confidential AI
CORDE uses Rust information-flow control and TEE ledger to declare data before disclosure in confidential VMs for AI.
Buyer’s guide rates 12 confidential computing options for 2026
The roundup contrasts Intel SGX/TDX and AMD SEV-SNP with cloud, EU, and web3 offerings, without new vulnerabilities.
1
2026 confidential computing ranking puts Azure first of ten
Editorial scores, not lab tests, place AWS Nitro Enclaves second and Google Cloud third, with Intel and AMD as silicon lanes.
1
Tinfoil replaces OVMF with about 300 lines of assembly
The company moved enclave boot measurement out of a million-line C firmware so an untrusted host cannot load arbitrary guest code.
1
Google Cloud plans NVIDIA Vera Rubin A5X instances next month
A5X pairs Vera Rubin NVL72 with ConnectX-9 networking, and Google plans capacity of up to 960,000 Rubin GPUs.
1
Anthropic acquires confidential computing startup Opaque Systems
Opaque’s team is joining Anthropic and winding down the company after a $24 million Series B at a $300 million valuation.
2
INTCC: A Framework for Interactive Confidential Computing
INTCC lets untrusted processors interactively work inside TEEs while keeping data confidential.
Trusted Model Environment for Private Semantic Computations
Researchers propose trusted model environments that run generative models inside TEEs for private semantic computation.
Meta locks itself out of user data on its AI glasses
Meta extended Private Processing to AI glasses so cloud AI runs without Meta accessing user data.
1
New DDRop Attack Breaks Intel TDX and AMD SEV-SNP With $159 DDR5 Device
DDRop uses a $159 DDR5 RDIMM interposer to silently drop memory writes and break Intel TDX and AMD SEV-SNP confidential VMs.
3
DDRop Attack Forces Intel TDX Confidential VMs Into Debug Mode and Exposes Memory
KU Leuven and ETH Zurich researchers released DDRop PoC hardware that forces Intel TDX confidential VMs into debug mode and exposes plaintext memory.
2
New hardware device can RAM into encrypted memory, expose your data
Researchers built a $200 DDR5 interposer that silently drops memory writes to break TDX, SGX, and SEV-SNP confidential VM integrity, requiring physical access.
2
New DDRop Attack Breaks Intel TDX and AMD SEV-SNP Confidential Computing
DDRop uses a sub-$200 DDR5 interposer to drop memory writes, breaking Intel TDX and AMD SEV-SNP confidentiality guarantees.
3
An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference
Odin runs Llama-3-8B fully homomorphic encrypted inference on a single H100 in 366 seconds, a 4.51x speedup over THOR.
A new open standard locks AI weights to approved hardware
OPAQUE releases Weight Custody Manifest, an open standard keeping AI model weights encrypted until receiving hardware cryptographically attests to builder-specified conditions.
2
Session Attestation for Unmodified TLS Services in Confidential Virtual Machines
SessionLatch adds session attestation to unmodified TLS services in confidential VMs, cutting short-upload latency 63.1% versus TNG on Hygon CSV.
Linux Foundation takes on TRACE, a hardware-backed runtime evidence specification for AI agents
The Linux Foundation adopts TRACE, an OPAQUE-contributed spec giving AI agents hardware-attested, cryptographically verifiable runtime and compliance evidence.
2