SGLang RCE exploited at NEAR AI; user and agent data taken
About 100 Private Chat accounts and 18 agents were exposed; two Cloud API keys were revoked and no CVE was named.
Stories per day · 30 days
4 RSS
Relatedintel-sgx3amd-sev2azure2confidential-computing2google-cloud2privacy2side-channel2ann1anonymous-authentication1attestability1aws1bishield-tee1data-breach1ddos1decision-trees1differential-privacy1doubly-oblivious1ethereum1
24 stories, newest first · one card per story
Stories tagged #tee
MammothDP hardens private boosted trees for trusted hardware
It adds privacy-free early stopping and rollback protection intended to resist timing side channels on TEEs.
O2N2 framework enables doubly oblivious approximate nearest neighbor search
O2N2 achieves 9.8-125.9x speedup over prior doubly oblivious ANN baselines on real-world datasets.
STAR uses server TEEs for anonymous rate limiting at scale
The design reports authentication in tens of microseconds and about 13.9K requests per second per CPU core.
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
KNOX runs generative models in a TEE regulatory sandbox
An attested monitor allows only matching tool and system calls, with authors reporting overhead under 1%.
Survey argues TEE attestation breaks can expose enclave secrets
Cited DRAM and memory attacks extracted SGX attestation keys and produced false AMD SEV-SNP reports.
Study compares TEE-enabled Ethereum rollup sequencer designs
Authors report small TEE overhead under both PBS and monolithic models, with PBS enabling faster builders.
BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
Unilateral TEE weight obfuscation for on-device LLMs is breakable; BiShield-TEE hides the key among ambiguous solutions.
Protecting CPU AI On Edge TEEs: WebAssembly's Promise and Practical Challenges
OP-TEE runs unaltered WebAssembly AI models on Arm TrustZone with 22% overhead and 6% extra latency.
PRA-TLS: Attestation of a Client Application for TEE
PRA-TLS attests client applications that call TEE enclaves, prototyped on Intel SGX.
Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy
Google moved Gboard federated learning into attested TEEs with externally verifiable differential privacy.
INTCC: A Framework for Interactive Confidential Computing
INTCC lets untrusted processors interactively work inside TEEs while keeping data confidential.
Toward verifiably private learning from federated data
A TEE-based federated learning system trains Gboard models faster under smaller, verifiable privacy budgets.
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
Verifiable Computation with Trusted Execution Environments and On-Chain Digital Rights Tokens
Researchers propose TEE-sealed data pools with on-chain Digital Rights Tokens so analysts run code without seeing underlying data.
Towards TEE-Certified DP: Verifiable Differentially Private Training on Legacy GPUs
Framework uses CPU TEEs with probabilistic checking to verifiably enforce differential privacy on GPU-offloaded gradient computation at modest overhead.
MicroHasTEE: Bare-Metal Haskell for Type-Level Peripheral Ownership on Armv8-M
MicroHasTEE expresses TrustZone secure and non-secure firmware as one typed Haskell program, catching peripheral-ownership inconsistencies at compile time.
"They don't care about this": A Systematic Study of TEE Build Reproducibility in the Wild
91% of 115 surveyed TEE deployments across Intel SGX, TDX, and AMD SEV fail to provide reproducible builds needed for verifiable remote attestation.
Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection
Researchers formalize obfuscation primitives for TEE-protected on-device LLMs and show a Collapse attack breaks ArrowCloak, TSQP, and LoRO, then extend the boundary.
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.
Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture
Hoss uses heterogeneous GPU-CPU TEEs for oblivious semantic search, achieving up to 67x speedup over the Compass ORAM-based system.