Trusted Execution Environments

Also known as TEE

Trusted Execution Environments (TEEs) isolate sensitive code and data from the operating system or host, while remote attestation lets users verify which hardware and software are running. Work applies these protections to confidential workloads such as LLM inference, API routing, and AI agents, using platforms including Intel TDX and Arm TrustZone. Common approaches combine attestation with split execution across trusted CPUs and untrusted GPUs, resource-isolation and scheduling techniques, or privacy methods such as differential privacy. The central tension is that stronger isolation and verification can add latency and constrain resources, while proof that code ran correctly does not by itself establish that the code or its safety policies are trustworthy.

Latest papers

12 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
Oct 15, 2026Zhiyuan Wang, Yuezhi Zhou, Ziqi Zhang +3LLM Security On-Device Language Model Inference
Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China · Zhongguancun Laboratory, Beijing, China · University of Illinois Urbana-Champaign, IL, USA
SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy
Sep 14, 2026Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar +1Privacy-Preserving Language Models Split Inference
School of Computing, Macquarie University
TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge
Aug 24, 2026Kurt M Wilson, Mohaiminul Al Nahian, Abeer Matar A. Almalky +5Efficient Neural Network Inference Edge Inference
North Carolina State University · Binghamton University (SUNY) · Florida International University +1
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Jun 22, 2026Yinpeng Wu, Yitong Chen, Lixiang Wang +3LLM Serving On-Device Language Model Inference
Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University
The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
Jun 15, 2026Sipeng Xie, Qianhong Wu, Hengrun Lu +4Remote Attestation LLM Agent Security
1Beihang University · 2Renmin University of China · 3Independent
Communication-Efficient Verifiable Attention for LLM Inference
Jun 15, 2026Ziqun Chen, Ming Wu, Michael Heinrich +4LLM Inference Trusted Execution Environments
Nanyang Technological University · Singapore · Zero Gravity Labs +1
Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack
Jun 2, 2026Yang Yang, Kevin Wang, Yuanhai Luo +4Cybersecurity Remote Attestation
OPPO · Phala
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
May 4, 2026Javad Forough, Marios Kogias, Hamed HaddadiCybersecurity Remote Attestation
Department of Computing Imperial College London London, United Kingdom
Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing
Apr 27, 2026Antony RowstronPrivacy Auditing AI Agent Auditing
Advanced Research and Invention Agency (ARIA) London, UK
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Mar 10, 2026Yinpeng Wu, Yitong Chen, Lixiang Wang +3LLM Serving On-Device Language Model Inference
Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
Mar 6, 2026Xisen Jin, Michael Duan, Qin Lin +4LLM Guardrails Remote Attestation
Sahara AI · University of Southern California
Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments
Feb 23, 2026Kunal Mukherjee, Spandan MukherjeeLLMs for Cybersecurity LLM Red Teaming
Virginia Tech Blacksburg, Virginia, USA · The University of Texas at Dallas Richardson, Texas, USA

Oct 15, 2026J/K move · Enter open · S save

BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition

Zhiyuan Wang, Yuezhi Zhou, Ziqi Zhang, Zhu Zhang+2

Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China · Zhongguancun Laboratory, Beijing, China · University of Illinois Urbana-Champaign, IL, USA

LLM Security On-Device Language Model Inference Trusted Execution Environments Model Extraction Attacks

Open paper AskPDF arXiv

On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models to reverse engineering and intellectual property theft. Trusted Execution Environments (TEEs) provide hardware-enforced isolation for on-device inference, yet most TEE-based parameter obfuscation relies on unilateral matrix transformations that obfuscate only the output side. We identify a vulnerability in this design, termed the Solution Determinacy Property (SDP): the obfuscation secret is uniquely determined, exposing the structure of the true key and enabling attackers to break the protection. Under our attacks, representative methods GroupCover and ArrowCloak are reduced to negligible protection, with attack accuracy reaching over 2.4 times the full-shielding black-box baseline and recovering near-complete model functionality. To address this vulnerability, we propose BiShield-TEE, a bilateral framework that induces Ambiguous Solutions through joint obfuscation of input and output dimensions, hiding the true key among many equally valid candidates. Experiments across diverse models and datasets show that BiShield-TEE confines attack accuracy to the full-shielding black-box baseline, while achieving higher inference efficiency than prior methods on real hardware. Our code is available at https://github.com/laduiw/BiShield-TEE.