no code implementations • 7 May 2024 • Ziyu Liu, Tong Zhou, Yukui Luo, Xiaolin Xu
Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices.
no code implementations • 18 Mar 2024 • Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren
To improve the accuracy of a small model, knowledge distillation is a popular method.
1 code implementation • ICCV 2023 • Hongwu Peng, Shaoyi Huang, Tong Zhou, Yukui Luo, Chenghong Wang, Zigeng Wang, Jiahui Zhao, Xi Xie, Ang Li, Tony Geng, Kaleel Mahmood, Wujie Wen, Xiaolin Xu, Caiwen Ding
The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues.
no code implementations • ICCV 2023 • Ruyi Ding, Shijin Duan, Xiaolin Xu, Yunsi Fei
Graph neural networks (GNNs) have brought superb performance to various applications utilizing graph structural data, such as social analysis and fraud detection.
1 code implementation • 28 Apr 2023 • Tong Zhou, Yukui Luo, Shaolei Ren, Xiaolin Xu
In this work, we propose an active model IP protection scheme, namely NNSplitter, which actively protects the model by splitting it into two parts: the obfuscated model that performs poorly due to weight obfuscation, and the model secrets consisting of the indexes and original values of the obfuscated weights, which can only be accessed by authorized users with the support of the trusted execution environment.
1 code implementation • 23 Feb 2023 • Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren
Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power.
no code implementations • 5 Feb 2023 • Hongwu Peng, Shanglin Zhou, Yukui Luo, Nuo Xu, Shijin Duan, Ran Ran, Jiahui Zhao, Shaoyi Huang, Xi Xie, Chenghong Wang, Tong Geng, Wujie Wen, Xiaolin Xu, Caiwen Ding
The proliferation of deep learning (DL) has led to the emergence of privacy and security concerns.
no code implementations • 20 Sep 2022 • Hongwu Peng, Shanglin Zhou, Yukui Luo, Shijin Duan, Nuo Xu, Ran Ran, Shaoyi Huang, Chenghong Wang, Tong Geng, Ang Li, Wujie Wen, Xiaolin Xu, Caiwen Ding
The rapid growth and deployment of deep learning (DL) has witnessed emerging privacy and security concerns.
no code implementations • 18 Sep 2022 • Xiaolin Xu, Yuan Zong, Wenming Zheng, Yang Li, Chuangao Tang, Xingxun Jiang, Haolin Jiang
In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks.
1 code implementation • 17 Aug 2022 • Tong Zhou, Shaolei Ren, Xiaolin Xu
Nonetheless, we observe that, with only extracting an obfuscated DNN architecture, the adversary can still retrain a substitute model with high performance (e. g., accuracy), rendering the obfuscation techniques ineffective.
1 code implementation • 18 Mar 2022 • Shijin Duan, Yejia Liu, Shaolei Ren, Xiaolin Xu
Thanks to the tiny storage and efficient execution, hyperdimensional Computing (HDC) is emerging as a lightweight learning framework on resource-constrained hardware.
1 code implementation • 9 Mar 2022 • Shijin Duan, Xiaolin Xu, Shaolei Ren
Nonetheless, they have two fundamental drawbacks, heuristic training process and ultra-high dimension, which result in sub-optimal inference accuracy and large model sizes beyond the capability of tiny devices with stringent resource constraints.
no code implementations • 5 Nov 2020 • Adnan Siraj Rakin, Yukui Luo, Xiaolin Xu, Deliang Fan
Specifically, she can aggressively overload the shared power distribution system of FPGA with malicious power-plundering circuits, achieving adversarial weight duplication (AWD) hardware attack that duplicates certain DNN weight packages during data transmission between off-chip memory and on-chip buffer, to hijack the DNN function of the victim tenant.
no code implementations • 20 Apr 2019 • Zimu Guo, Xiaolin Xu, Mark M. Tehranipoor, Domenic Forte
These modules guarantee the stream cipher is correctly synchronized and free from tampering.
Cryptography and Security