检索结果-内蒙古大学图书馆

A Survey of Integrating Generative Artificial Intelligence and 6G Mobile Services: Architectures, Solutions, Technologies and Outlooks

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Liu, Yi-Jing Du, Hongyang Xu, Xinyi Zhang, Ruichen Feng, Gang Cao, Bin Niyato, Dusit Kim, Dong In Jamalipour, Abbas Letaief, Khaled B. Tafazolli, Rahim University of Electronic Science and Technology of China National Key Lab on Wireless Communications Chengdu China University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Nanyang Technological University College of Computing and Data Science Singapore Singapore Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of University of Sydney School of Electrical and Computer Engineering Sydney Australia Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong University of Surrey Institute for Communication Systems School of Computer Science and Electronic Engineering United Kingdom

Generative artificial intelligence (GenAI) is rapidly driving a new phase of artificial intelligence revolution, marked by various applications such as ChatGPT, Sora and DeepSeek. With powerful capabilities in content generation, personalization and user interaction, GenAI can drive significant enhancements in various mobile services to satisfy individual user preferences. Meanwhile, mobile services offer substantial support for accessibility, functionality and intelligence of GenAI applications. However, current research on integrating GenAI and mobile services remains nascent, lacking necessary theoretical and technical support. In this survey, we break down a new vision to guide research on integrating GenAI and mobile services, aiming to improve 6G intelligence levels and enable 6G mobile networks to support the integration of GenAI and mobile services effectively. We begin by examining the necessity of integrating GenAI with 6G mobile services and exploring potential learning architectures of GenAI models within mobile networks. Next, we analyze potential solutions from two perspectives: how 6G mobile networks empower GenAI and how GenAI enables mobile services. We subsequently explore a promising use case, along with essential features and techniques, to facilitate the integration of GenAI and mobile services. Finally, we discuss future research directions, aiming at realizing intelligent 6G networks. © 2015 IEEE.

关键词： Generative adversarial networks

Unsupervised Multi-shot Person Re-identification via Dynamic Bi-directional Normalized Sparse Representation 27th

学校读者我要写书评

暂无评论

Unsupervised Multi-shot Person Re-identification via Dynamic...

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Li, Xiaobao Wang, Wen Li, Qingyong Guo, Lijun Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo Zhejiang China

ISBN: (纸本)9783030678319

Due to the abundant priori information and the widespread applications, multi-shot based person re-identification has drawn increasing attention in recent years. In this paper, the high labeling cost and the huge unlabeled data motivate us to focus on the unsupervised scenario and a unified coarse-to-fine framework is proposed, named by Dynamic Bi-directional Normalized Sparse Representation (DBNSR). Specifically, the method designs an alternatively iterative mechanism to dynamically update the estimated cross-camera labels and progressively learn a discriminative metric. In each iteration, a Bi-directional Normalized Sparse Representation (BNSR) model is applied to estimate the label for each pair of cross-camera person sequences with bi-directional probabilities defined to encode their mutual correlation. With the estimated labels, we learn a keep-it-simple-and-straight-forward metric (KISSME) to further make BNSR model available in a more discriminative and lower-dimensional subspace. Extensive experiments on PRID 2011, iLIDS-VID and MARS three benchmarks show that our method performs favorably against state-of-the-arts. © 2021, Springer Nature Switzerland AG.

关键词： Cameras

SP3: Enhancing Structured Pruning via PCA Projection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Yuxuan Zhang, Jing Zhao, Zhe Zhao, Chen Chen, Xiaodong Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China Tencent AI Lab Tencent Beijing China School of Computer Science and Technology Xi'an Jiaotong University Xi'An China

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection (SP3), targeting the effective reduction of d by projecting features into a space defined by principal components before masking. Extensive experiments on benchmarks (GLUE and SQuAD) show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy and outperform other methods that compress d by 6% in accuracy at the same compression ratio. SP3 has also proven effective with other models, including OPT and Llama. Our data and code are available at ours repo. © 2023, CC BY.

关键词：

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China School of Information and Communication Technology Griffith University Australia University of Technology Sydney Australia RMIT University Australia

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: SPONGE for triggering widespread misidentifications and BLINDING for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (∼10%-60% absolute and ∼2-7× relative) in attack efficacy over state-of-the-art attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Denial-of-service attack

Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Wen Han, Bing Chen, Zhengyang Wang, Shuai Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain adaptation scenarios where some unlabeled target domain data is available. However, these methods often have limited performance improvement and lack generalization in various mismatch situations. In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning. For prototype contrastive learning, we generate pseudo labels via clustering to create dynamically updated prototype representations, aligning instances with their corresponding class or cluster prototypes. For instance contrastive learning, we minimize the distance between different views or augmentations of the same instance, ensuring robust and invariant representations resilient to variations like noise. This dual-level approach provides both high-level and low-level supervision, leading to improved generalization and robustness of the speaker verification model. Unlike previous studies that only evaluated mismatches in one situation, we have conducted relevant explorations on various datasets and achieved state-of-the-art performance currently, which also proves the generalization of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei 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 Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

An RTDNN-Based Hybrid Precoding and Combining Joint Optimization Algorithm for MUPC-MIMO Systems

学校读者我要写书评

暂无评论

IEEE Transactions on Green Communications and Networking

IEEE Transactions on Green Communications and Networking 2025年

作者： Liu, Fulai Liu, Yubiao Yang, Xianghuan Duan, Zhuoyao Shi, Baozhu Ji, Li Du, Ruiyan Northeastern University at Qinhuangdao Lab of Key Technology of Millimeter-wave Large-scale MIMO System Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao066004 China Hebei University College of Mathematics and Information Science Baoding071002 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Qinhuangdao Vocational and Technical College Qinhuangdao066100 China School of Computer Science and Engineering Northeastern University Shenyang110004 China

To achieve a satisfactory balance between energy efficiency (EE) and spectral efficiency (SE) for hybrid precoding and combining (HPC), this paper presents a two-stage joint optimization HPC algorithm based on residual deep neural network (DNN) for multi-user partially connected (MUPC) structure, namely RTDNN algorithm. In the proposed algorithm, a two-stage framework is designed to optimize analog and digital coders at the transmitter and receiver simultaneously, which can effectively preserve coupling relationship of coders between the transmitter and receiver. Specially, the RTDNN architecture is mainly divided into two stage networks, which includes analog stage and digital stage networks. The analog stage network is developed to obtain the optimal analog precoder and combiner simultaneously. On this basis, the digital stage network is constructed to solve the digital precoder and combiner concurrently. To further improve the prediction accuracy of RTDNN-based HPC, residual modules are adopted into the developed two stage networks. Moreover, the proposed RTDNN is trained with unsupervised learning. Simulation results show that the EE of the proposed algorithm is at least enhanced by 0.6 bits/Hz/J with satisfactory SE than other methods. © 2017 IEEE.

关键词： Deep neural networks

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

PS3: Precise Patch Presence Test based on Semantic Symbolic Signature

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhan, Qi Xia, Xin Hu, Xing Lo, David Li, Zhiyang Li, Shanping The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Software Engineering Application Technology Lab China Singapore Management University Singapore Zhejiang University Hangzhou China

During software development, vulnerabilities have posed a significant threat to users. Patches are the most effective way to combat vulnerabilities. In a large-scale software system, testing the presence of a security patch in every affected binary is crucial to ensure system security. Identifying whether a binary has been patched for a known vulnerability is challenging, as there may only be small differences between patched and vulnerable versions. Existing approaches mainly focus on detecting patches that are compiled in the same compiler options. However, it is common for developers to compile programs with very different compiler options in different situations, which causes inaccuracy for existing methods. In this paper, we propose a new approach named PS3, referring to precise patch presence test based on semantic-level symbolic signature. PS3 exploits symbolic emulation to extract signatures that are stable under different compiler options. Then PS3 can precisely test the presence of the patch by comparing the signatures between the reference and the target at semantic level. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 3,631 (CVE, binary) pairs of 62 recent CVEs in four C/C++ projects. The experimental results show that PS3 achieves scores of 0.82, 0.97, and 0.89 in terms of precision, recall, and F1 score, respectively. PS3 outperforms the state-of-the-art baselines by improving 33% in terms of F1 score and remains stable in different compiler options. © 2023, CC BY.

关键词： Software design