检索结果-内蒙古大学图书馆

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

A 0.9–1.4-GHz Q-Enhanced CMOS Tunable Bandpass Filter With Constant Fractional Bandwidth and Two Transmission Zeros

学校读者我要写书评

暂无评论

IEEE Microwave and Wireless technology Letters 2023年第6期33卷 667-670页

作者： Kun Li Xiang Li Shuangyang Wu Pei-Ling Chi Tao Yang School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu China Research Center of Advanced RF Chips and Systems Nanhu Laboratory Jiaxing China Department of Electrical and Computer Engineering National Chiao Tung University Hsinchu Taiwan

A tunable differential $Q$ -enhanced bandpass filter covering 0.9–1.4 GHz with constant fractional bandwidth (FBW) is proposed using 40-nm CMOS technology in this letter. The proposed filter is constructed by two resonators which consist of ON-chip integrated inductors and varactors. The inductors of the two resonators are placed close to each other to form the mainline magnetic coupling of the filter. Besides the mainline coupling, the source port and load port are connected directly by capacitors, forming the source-to-load coupling. With the proposed structure, two transmission zeros (TZs) can be obtained, which can greatly increase the stopband rejection. Meanwhile, nMOS cross-coupled pairs are used as the $Q$ -enhanced cells to reduce the insertion loss (IL) and further improve the filter selectivity. A filter prototype based on 40-nm CMOS process is fabricated to validate the proposed structure. The center frequency (CF) of the proposed filter can be tuned from 0.9 to 1.4 GHz while keeping the FBW constant at 8%.

关键词： Resonator filters Band-pass filters Microwave filters Filtering theory Couplings Equivalent circuits Magnetic separation

No Free Lunch Theorem for Privacy-Preserving LLM Inference

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xiaojin Fei, Yulin Kang, Yan Chen, Wei Fan, Lixin Jin, Hai Yang, Qiang Huazhong University of Science and Technology China WeBank China Hong Kong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable tasks. Furthermore, LLMs possess the capacity to sift through extensive datasets, uncover underlying patterns, and furnish critical insights that propel the frontiers of technology and science. However, LLMs also pose privacy concerns. Users’ interactions with LLMs may expose their sensitive personal or company information. A lack of robust privacy safeguards and legal frameworks could permit the unwarranted intrusion or improper handling of individual data, thereby risking infringements of privacy and the theft of personal identities. To ensure privacy, it is essential to minimize the dependency between shared prompts and private information. Various randomization approaches have been proposed to protect prompts’ privacy, but they may incur utility loss compared to unprotected LLMs prompting. Therefore, it is essential to evaluate the balance between the risk of privacy leakage and loss of utility when conducting effective protection mechanisms. The current study develops a framework for inferring privacy-protected Large Language Models (LLMs) and lays down a solid theoretical basis for examining the interplay between privacy preservation and utility. The core insight is encapsulated within a theorem that is called as the NFL (abbreviation of the word No-Free-Lunch) Theorem. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

Adaptive Sparse Channel Estimation for RIS-Assisted Mmwave Massive MIMO Systems

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular technology 2025年

作者： Shao, Shuying Lv, Tiejun Du, Siying Zeng, Jie Tan, Fangqing Lin, Zhipeng School of Information and Communication Engineering Beijing100876 China Shandong Institute of Petroleum and Chemical Technology Department of Computer Science and Engineering Dongying257061 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China Guilin University of Electronic Technology School of Information and Communication Guilin541004 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China

The integration of reconfigurable intelligent surfaces (RISs) with millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems holds significant promise for future wireless communication methods aiming to achieve high-speed data transmission and expand communication coverage. However, channel estimation (CE) in RIS-assisted wireless communication systems faces many challenges due to the limited signal processing capability of the RIS. Existing methods often fail to fully capture the non-uniform sparsity of mmWave channels. To address this limitation, we propose an adaptive sparse CE scheme involving two progressive algorithms, i.e., normalized least mean squares–log sum (NLMS-LOG) and normalized least mean squares–normalized least mean fourth–log sum (NLMS-NLMF-LOG), for RIS-assisted mmWave massive MIMO systems. The proposed scheme selectively adjusts the channel coefficients to improve the accuracy of the estimation, enabling more efficient exploitation of the inherent non-uniform sparsity in mmWave channels. The NLMS-LOG algorithm innovatively incorporates a log-sum penalty term into the cost function of the NLMS algorithm, thereby increasing the convergence rate. Building upon NLMS-LOG, the NLMS-NLMF-LOG algorithm employs a mixed error function to achieve superior performance across different SNR conditions. The simulation results demonstrate that the proposed scheme outperforms existing methods, such as the NLMS, sparse exponential forgetting window least mean square, and sparse hybrid adaptive filtering algorithms, in terms of CE accuracy and convergence speed. © 1967-2012 IEEE.

关键词： Cost functions

Extended Tool for Nanoparticles Incorporation Evaluation from Hyperspectral Images of Cultured Cells

学校读者我要写书评

暂无评论

Extended Tool for Nanoparticles Incorporation Evaluation fro...

International Conference on Semiconductor

作者： Ionela Nicoleta Irimescu Mihaela Deaconu Daniela Berger Nicolae Tarba Cosmin Catalin Mustaciosu Diana Iulia Savu Roxana-Cristina Popescu Eugen Scarlat Mona Mihailescu Simona Ioniță Ana Maria Pleava Applied Sciences Doctoral School National University of Science and Technology Politehnica Bucharest Medist Imaging & Point of Care Bucharest Romania CAMPUS Research Institute National University of Science and Technology Politehnica Bucharest Romania Department of Inorganic Chemistry Physical Chemistry & Electrochemistry National University of Science and Technology Politehnica Bucharest Romania Computer Sciences Doctoral School Physics Department National University of Science and Technology Politehnica Bucharest Romania Department of Life and Environmental Sciences “Horia Hulubei” National Institute for Research and Development in Physics and Nuclear Engineering Magurele Romania Department of Bioengineering and Biotechnology Faculty of Medical Engineering Politehnica Bucharest Romania Physics Department National University for Science and Technology Politehnica Bucharest Bucharest Romania Physics Department Fundamental Sciences Applied in Engineering Research Center CAMPUS Research Center Politehnica University Bucharest Romania Chemical Engineering Doctoral School National University of Science and Technology Politehnica Bucharest Romania CAMPUS Research Center U. N. S. T. National University of Science and Technology Politehnica Bucharest Romania

ISBN: (数字)9798350352078

ISBN: (纸本)9798350352085

Hyperspectral images of cultured cells incubated with mesoporous silica-based nanoparticles (NPs) functionalized with phenylboronic acid derivative and loaded with doxorubicin and resveratrol were analyzed to establish incorporation percentage. We designed and developed a digital tool, which extended the standard procedure, by combining spectral angle mapper with assisted segmentation and counting operations. It provides the percentage of pixels in which the spectral fingerprint of the NPs is found. The analysis is carried out at the cell level and points out the similarities and differences between cell lines and types of NPs.

关键词： Nanoparticles Image segmentation Microscopy Cells (biology) Fingerprint recognition Fibroblasts Breast cancer Mesoporous materials Standards Hyperspectral imaging

Spatial-Temporal Transformer based Video Compression Framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Yanbo Huang, Wenjia Li, Shuai Yuan, Hui Ye, Mao Ma, Siwei School of Software Shandong University Jinan China School of Control Science and Engineering Shandong University Jinan China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

Learned video compression (LVC) has witnessed remarkable advancements in recent years. Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented with neural networks (NNs). However, within the framework of NNs and its training mechanism using gradient backpropagation, most existing works often struggle to consistently generate stable motion information, which is in the form of geometric features, from the input color features. Moreover, the modules such as the inter-prediction and residual coding are independent from each other, making it inefficient to fully reduce the spatial-temporal redundancy. To address the above problems, in this paper, we propose a novel Spatial-Temporal Transformer based Video Compression (STT-VC) framework. It contains a Relaxed Deformable Transformer (RDT) with Uformer based offsets estimation for motion estimation and compensation, a Multi-Granularity Prediction (MGP) module based on multi-reference frames for prediction refinement, and a Spatial Feature Distribution prior based Transformer (SFD-T) for efficient temporal-spatial joint residual compression. Specifically, RDT is developed to stably estimate the motion information between frames by thoroughly investigating the relationship between the similarity based geometric motion feature extraction and self-attention. MGP is designed to fuse the multi-reference frame information by effectively exploring the coarse-grained prediction feature generated with the coded motion information. SFD-T is to compress the residual information by jointly exploring the spatial feature distributions in both residual and temporal prediction to further reduce the spatial-temporal redundancy. Experimental results demonstrate that our method achieves the best result with 13.5% BD-Rate saving over VTM and 68.7% BD-Rate saving over the baseline without the proposed modules. Ablation study validates the effectiveness

关键词： Image compression

Radio-Frequency Pseudo-Null Induced by Light in an Ion Trap

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chung, Daun Cha, Yonghwan Shon, Hosung Park, Jeonghyun Lee, Woojun Lee, Kyungmin Cho, Beomgeun Choi, Kwangyeul Kim, Chiyoon Yoo, Seungwoo Kim, Suhan Jeong, Uihwan Kang, Jiyong You, Jaehun Kim, Taehyun Dept. of Computer Science and Engineering Seoul National University Seoul08826 Korea Republic of Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of NextQuantum Seoul National University Seoul08826 Korea Republic of Institute of Computer Technology Seoul National University Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Seoul08826 Korea Republic of Institute of Applied Physics Seoul National University Seoul08826 Korea Republic of

In a linear radio-frequency (rf) ion trap, the rf null is the point of zero electric field in the dynamic trapping potential where the ion motion is approximately harmonic. When displaced from the rf null, the ion is superimposed by fast oscillations known as micromotion, which can be probed through motion-sensitive light-atom interactions. In this work, we report on the emergence of the rf pseudo-null, a locus of points where the ion responds to light as if it were at the true rf null, despite being displaced from it. The phenomenon is fully explained by accounting for the general two-dimensional structure of micromotion and is experimentally verified under various potential configurations, with observations in great agreement with numerical simulations. The rf pseudo-null manifests as a line in a two-dimensional parameter space, determined by the geometry of the incident light and its overlap with the motional structure of the ion. The true rf null occurs uniquely at the concurrent point of the pseudo-null lines induced by different light sources. © 2025, CC BY.

关键词：

Design and Implementation of a Following Vehicle Based on ROS and UWB

学校读者我要写书评

暂无评论

Design and Implementation of a Following Vehicle Based on RO...

Automation, Control and Robots (ICACR), International Conference on

作者： Yun-Shuai Yu Chin-Wei Chen Department of Computer Science and Information Engineering National Formosa University Yunlin Taiwan Software Research & Development Center Hon Hai Technology Group (Foxconn) New Taipei City Taiwan

Autonomous vehicle technology has gained significant attention in various industries recently. This paper presents the design and implementation of a following vehicle that utilizes the Robot Operating System (ROS) and Ultra-Wideband (UWB) RF transceiver modules to achieve precise target localization, map the surrounding environment, and navigate accordingly. A mobile application has also been developed to track the following vehicle’s position.

关键词：

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Doubl...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：