TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge

• URL: http://arxiv.org/abs/2608.22716v1
• Date: Mon, 24 Aug 2026 02:05:26 GMT
• Title: TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge
• Abstract summary: TEE-X is a TEE-aware acceleration framework that introduces a sensitivity-aware modularization technique and enables vectorization in TEE inference.<n>The design is validated on OP-TEE for Arm TrustZone, configured to optimize performance on the NVIDIA Jetson AGX Xavier for efficient edge vision applications.
• Score: 15.135142694332322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their remarkable success, machine learning models, particularly in vision applications, are alarmingly vulnerable to a range of security threats. One key factor in the attack landscape is the distinction between white-box and black-box threat models, as the latter poses challenges that limit attack effectiveness when access to model information is limited. As a result, using Trusted Execution Environments (TEEs) enhances security for machine learning applications by protecting model confidentiality and execution integrity, effectively shifting the execution environment from the white-box to the black-box side of the threat model spectrum. While adopting TEEs for large vision models, e.g., Vision Transformers (ViTs), is crucial for enhancing security and privacy, significant challenges related to memory constraints and increased computational latency must be addressed, especially in time-sensitive edge applications where safety and privacy are paramount. The objective of this work is to enable large vision models to be fully hosted within TEEs, achieving GPU-level inference latency for time-sensitive edge vision applications while maintaining performance. To this end, we propose TEE-X, a TEE-aware acceleration framework that introduces a sensitivity-aware modularization technique and enables vectorization in TEE inference. This design is validated on OP-TEE for Arm TrustZone, configured to optimize performance on the NVIDIA Jetson AGX Xavier for efficient edge vision applications using ViT models. The findings reveal that TEE-X delivers an effective TEE-aware acceleration framework that achieves minimal accuracy-latency trade-offs while ensuring fast and secure edge inference for vision models.

Related papers

• DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization [65.89030524420933]
  DiSCO is a zero-shot, strictly black-box defense that operates entirely at the prompt level as a plug-and-play module.<n>We demonstrate that DiSCO consistently enhances the safety of both undefended and defended models.<n>As a black-box, architecture-agnostic module, DiSCO can be readily applied to any text-to-image system.
  arXiv  Detail & Related papers  (2026-08-17T19:13:55Z)
• SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability [49.074914896839466]
  We introduce SafeVision, a novel image guardrail that integrates human-like reasoning to enhance adaptability and transparency.<n>Our approach incorporates an effective data collection and generation framework, a policy-following training pipeline, and a customized loss function.<n>We show that SafeVision achieves state-of-the-art performance on different benchmarks.
  arXiv  Detail & Related papers  (2025-10-28T00:35:59Z)
• SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deployment [9.666696979829359]
  SecureInfer is a framework that offloads compute-intensive operations to untrusted accelerators.<n>We implement a prototype of SecureInfer using the LLaMA-2 model and evaluate it across performance and security metrics.
  arXiv  Detail & Related papers  (2025-10-22T19:17:31Z)
• Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators [19.93096649006403]
  Machine learning runs on untrusted cloud infrastructure, exposing data and models to potential breaches.<n>Running model inference entirely within trusted execution environments (TEEs) is subject to non-trivial slowdown.<n>We propose TwinShield, a framework enabling secure Transformer inference in heterogeneous TEE and accelerator systems.
  arXiv  Detail & Related papers  (2025-07-04T03:52:53Z)
• TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE [15.680713503694951]
  Existing wisdom deploys models within Trusted Execution Environments (TEEs)<n>This paper fills the gap withShield, the first efficient on-device inference work that shields partial tensors of the model while still fully defending against MS and MIA.
  arXiv  Detail & Related papers  (2025-05-28T18:00:24Z)
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning [69.72249695674665]
  We propose a robust test-time prompt tuning (R-TPT) for vision-language models (VLMs)<n>R-TPT mitigates the impact of adversarial attacks during the inference stage.<n>We introduce a plug-and-play reliability-based weighted ensembling strategy to strengthen the defense.
  arXiv  Detail & Related papers  (2025-04-15T13:49:31Z)
• Intelligent IoT Attack Detection Design via ODLLM with Feature Ranking-based Knowledge Base [0.964942474860411]
  Internet of Things (IoT) devices have introduced significant cybersecurity challenges.<n>Traditional machine learning (ML) techniques often fall short in detecting such attacks due to the complexity of blended and evolving patterns.<n>We propose a novel framework leveraging On-Device Large Language Models (ODLLMs) augmented with fine-tuning and knowledge base (KB) integration for intelligent IoT network attack detection.
  arXiv  Detail & Related papers  (2025-03-27T16:41:57Z)
• Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense [90.71884758066042]
  Large vision-language models (LVLMs) introduce a unique vulnerability: susceptibility to malicious attacks via visual inputs.<n>We propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism.
  arXiv  Detail & Related papers  (2025-03-14T17:39:45Z)
• Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment [59.61554561979589]
  Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios.<n>Existing edge detection methods face challenges: difficulty balancing detection precision with lightweight models, limited adaptability, and insufficient real-world validation.<n>We propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments.
  arXiv  Detail & Related papers  (2024-12-24T07:28:10Z)
• TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models [12.253529209143197]
  TSDP is a method that protects privacy-sensitive weights within TEEs and offloads insensitive weights to GPUs. We introduce a novel partition before training strategy, which effectively separates privacy-sensitive weights from other components of the model. Our evaluation demonstrates that our approach can offer full model protection with a computational cost reduced by a factor of 10.
  arXiv  Detail & Related papers  (2024-11-15T04:52:11Z)
• Enhancing Physical Layer Communication Security through Generative AI with Mixture of Experts [80.0638227807621]
  generative artificial intelligence (GAI) models have demonstrated superiority over conventional AI methods. MoE, which uses multiple expert models for prediction through a gate mechanism, proposes possible solutions.
  arXiv  Detail & Related papers  (2024-05-07T11:13:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.