paper-with-me

홈 › Papers

TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments

2024-05-07 · Ziyu Liu, Tong Zhou, Yukui Luo, Xiaolin Xu

Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or introduce large performance overhead. Taking both security and performance into consideration, this paper presents TBNet, a TEE-based defense framework that protects DNN model from a neural architectural perspective. Specifically, TBNet generates a novel Two-Branch substitution model, to respectively exploit (1) the computational resources in the untrusted Rich Execution Environment (REE) for latency reduction and (2) the physically-isolated TEE for model protection. Experimental results on a Raspberry Pi across diverse DNN model architectures and datasets demonstrate that TBNet achieves efficient model protection at a low cost.

📄 PDF Abstract BibTeX arXiv:2405.03974

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch

2026-03-13 · Qichen Zhao, Shengfang Zhai, Xinjian Bai, Qingni Shen 외 arxiv

Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation. To mitigate these risks, proactive image protection methods embed small, often …

Image Editing

MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security

2026-04-08 · Mehrdad Rostamzadeh, Sidhant Narula, Nahom Birhan, Mohammad Ghasemigol 외 arxiv

The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unli…

Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network

2018-06-01 · CVPR 2018 6 · Wenda Zhao, Fan Zhao, Dong Wang, Huchuan Lu

Defocus blur detection (DBD) is the separation of infocus and out-of-focus regions in an image. This process has been paid considerable attention because of its remarkable potential applications. Accurate differentiation…

Defocus Blur DetectionDefocus Estimation

TBNet:Two-Stream Boundary-aware Network for Generic Image Manipulation Localization

2021-08-10 · Zan Gao, Chao Sun, Zhiyong Cheng, Weili Guan 외

Finding tampered regions in images is a hot research topic in machine learning and computer vision. Although many image manipulation location algorithms have been proposed, most of them only focus on the RGB images with …

Image ManipulationImage Manipulation Localization

SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition

2025-10-01 · Chenxiang Luo, David K. Y. Yau, Qun Song arxiv

Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where adversaries reconstruct private data from shared gradients. Existing def…

Human Activity RecognitionImage ClassificationFederated LearningKeyword Spotting