检索结果-内蒙古大学图书馆

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yinqiu Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In Jamalipour, Abbas The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of The School of Electrical and Information Engineering University of Sydney Australia

With the phenomenal success of diffusion models and ChatGPT, deep generation models (DGMs) have been experiencing explosive growth from 2022. Not limited to content generation, DGMs are also widely adopted in Internet of Things, Metaverse, and digital twin, due to their outstanding ability to represent complex patterns and generate plausible samples. In this article, we explore the applications of DGMs in a crucial task, i.e., improving the efficiency of wireless network management. Specifically, we firstly overview the generative AI, as well as three representative DGMs. Then, a DGM-empowered framework for wireless network management is proposed, in which we elaborate the issues of the conventional network management approaches, why DGMs can address them efficiently, and the step-by-step workflow for applying DGMs in managing wireless networks. Moreover, we conduct a case study on network economics, using the state-of-the-art DGM model, i.e., diffusion model, to generate effective contracts for incentivizing the mobile AI-Generated Content (AIGC) services. Last but not least, we discuss important open directions for the further research. © 2023, CC BY.

关键词： Wireless networks

Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaohui Yi, Jiangyan Tao, Jianhua Wang, Chenglong Zhang, Chuyuan State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Information Technology University of Beijing Jiaotong Beijing China Department of Automation Tsinghua University Beijing China University of Science and Technology of China Beijing China

Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset. The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets. To overcome this limitation, we propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting, called Regularized Adaptive Weight Modification (RAWM). When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. The adaptive modification direction ensures the network can effectively detect fake audio on the new dataset while preserving its knowledge of old model, thus mitigating catastrophic forgetting. In addition, genuine audio collected from quite different acoustic conditions may skew their feature distribution, so we introduce a regularization constraint to force the network to remember the old distribution in this regard. Our method can easily be generalized to related fields, like speech emotion recognition. We also evaluate our approach across multiple datasets and obtain a significant performance improvement on cross-dataset experiments. © 2023, CC BY.

关键词： Emotion Recognition

Hierarchical Micro-Segmentations for Zero-Trust Services via Large Language Model (LLM)-enhanced Graph Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yinqiu Liu, Guangyuan Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui In Kim, Dong Shen, Xuemin College of Computing and Data Science Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Department of Electrical and Computer Engineering University of Waterloo Canada

—In the rapidly evolving Next-Generation Networking (NGN) era, the adoption of zero-trust architectures has become increasingly crucial to protect security. However, provisioning zero-trust services in NGNs poses significant challenges, primarily due to the environmental complexity and dynamics. Motivated by these challenges, this paper explores efficient zero-trust service provisioning using hierarchical micro-segmentations. Specifically, we model zero-trust networks via hierarchical graphs, thereby jointly considering the resource- and trust-level features to optimize service efficiency. We organize such zero-trust networks through micro-segmentations, which support granular zero-trust policies efficiently. To generate the optimal micro-segmentation, we present the Large Language Model-Enhanced Graph Diffusion (LEGD) algorithm, which leverages the diffusion process to realize a high-quality generation paradigm. Additionally, we utilize policy boosting and Large Language Models (LLM) to enable LEGD to optimize the generation policy and understand complicated graphical features. Moreover, realizing the unique trustworthiness updates or service upgrades in zero-trust NGN, we further present LEGD-Adaptive Maintenance (LEGD-AM), providing an adaptive way to perform task-oriented fine-tuning on LEGD. Extensive experiments demonstrate that the proposed LEGD achieves 90% higher efficiency in provisioning services compared with other baselines. Moreover, the LEGD-AM can reduce the service outage time by over 50%. © 2024, CC BY.

关键词： Diffusion

What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaohui Yi, Jiangyan Wang, Chenglong Zhang, Chuyuan Zeng, Siding Tao, Jianhua State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Information Technology University of Beijing Jiaotong Beijing China Department of Automation Tsinghua University Beijing China University of Science and Technology of China Beijing China

The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition. © 2023, CC BY.

关键词： Image recognition

ALIM: adjusting label importance mechanism for noisy partial label learning 23

学校读者我要写书评

暂无评论

ALIM: adjusting label importance mechanism for noisy partial...

Proceedings of the 37th International Conference on Neural information Processing systems

作者： Mingyu Xu Zheng Lian Lei Feng Bin Liu Jianhua Tao The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Computer Science and Engineering Nanyang Technological University Department of Automation Tsinghua University and Beijing National Research Center for Information Science and Technology Tsinghua University

Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate label set. To address this challenging problem, most of the existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample. However, detection errors are unavoidable. These errors can accumulate during training and continuously affect model optimization. To this end, we propose a novel framework for noisy PLL with theoretical interpretations, called "Adjusting Label Importance Mechanism (ALIM)". It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs. ALIM is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets demonstrate that our method can achieve state-of-the-art performance on noisy PLL. Our code is available at: https://***/zeroQiaoba/ALIM.

关键词：

Privacy Attacks and Defenses for Digital Twin Migrations in Vehicular Metaverses

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luo, Xiaofeng Wen, Jinbo Kang, Jiawen Nie, Jiangtian Xiong, Zehui Zhang, Yang Yang, Zhaohui Xie, Shengli School of Automation Guangdong University of Technology China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China School of Computer Science and Engineering Nanyang Technological University Singapore Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore College of Information Science and Electronic Engineering Zhejiang University China

The gradual fusion of intelligent transportation systems with metaverse technologies is giving rise to vehicular metaverses, which blend virtual spaces with physical space. As indispensable components for vehicular metaverses, Vehicular Twins (VTs) are digital replicas of Vehicular Metaverse Users (VMUs) and facilitate customized metaverse services to VMUs. VTs are established and maintained in RoadSide Units (RSUs) with sufficient computing and storage resources. Due to the limited communication coverage of RSUs and the high mobility of VMUs, VTs need to be migrated among RSUs to ensure real-time and seamless services for VMUs. However, during VT migrations, physical-virtual synchronization and massive communications among VTs may cause identity and location privacy disclosures of VMUs and VTs. In this article, we study privacy issues and the corresponding defenses for VT migrations in vehicular metaverses. We first present four kinds of specific privacy attacks during VT migrations. Then, we propose a VMU-VT dual pseudonym scheme and a synchronous pseudonym change framework to defend against these attacks. Additionally, we evaluate average privacy entropy for pseudonym changes and optimize the number of pseudonym distribution based on inventory theory. Numerical results show that the average utility of VMUs under our proposed schemes is 33.8% higher than that under the equal distribution scheme, demonstrating the superiority of our schemes. © 2023, CC BY.

关键词： Computation theory

Freshness-aware Incentive Mechanism for Mobile AI-Generated Content (AIGC) Networks

学校读者我要写书评

暂无评论

Freshness-aware Incentive Mechanism for Mobile AI-Generated ...

IEEE International Conference on Communications in China (ICCC)

作者： Jinbo Wen Jiawen Kang Minrui Xu Hongyang Du Zehui Xiong Yang Zhang Dusit Niyato College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China School of Automation Guangdong University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Artificial Intelligence-Generated Content (AIGC) is a rapidly growing field that uses advanced AI algorithms to automatically generate, manipulate, and modify data to create diverse and valuable content. Recently, mobile AIGC networks have attracted significant attention. They integrate with mobile edge networks to provide customized and personalized AIGC services in real time. This is achieved by deploying AI algorithms on edge devices, particularly on Unmanned Aerial Vehicles (UAVs) with edge servers in a flexible and dynamic manner for ubiquitous edge intelligence. However, the wide deployment of UAV-enabled AIGC still faces critical challenges, such as issues with data freshness for AIGC fine-tuning and concerns around incentivizing fresh data sharing among UAVs under information asymmetry. In this paper, we first utilize Age of information (AoI) as a well-accepted data-freshness metric to quantify data freshness for AIGC fine-tuning. Then, we propose an AoI-based contract theory model to incentivize the contribution of fresh data among UAVs. Moreover, we design the optimal contract that is feasible to maximize the expected utility of the base station that is responsible for dispatching UAVs to collaboratively perform AIGC tasks. Finally, numerical results demonstrate the effectiveness of the proposed scheme in mobile AIGC networks.

关键词：

A Two-Stage Enhancement Method for Object Detection on Low-Resolution Images

学校读者我要写书评

暂无评论

A Two-Stage Enhancement Method for Object Detection on Low-R...

International Joint Conference on Neural Networks (IJCNN)

作者： Zijian Yuan Mingyang Ling Kan Chang Mengyu Yin Minghong Li Boning Chen School of Computer and Electronic Information Guangxi University Nanning China School of Electrical Engineering Guangxi University Nanning China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China School of Automation Central South University Changsha China School of Computing and Information Systems The University of Melbourne Melbourne Australia

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Detecting objects on low-resolution (LR) images is a challenging task, as small structures and details contained in LR images are insufficient. To improve the detection accuracy on LR images, a two-stage enhancement framework is proposed in this paper. In the first stage, a lightweight image super-resolution (SR) sub-network is built by incorporating the external guidance obtained by the detection backbone, so that the potential discriminant features can be well preserved. Moreover, to alleviate the hardship of directly learning a nonlinear mapping from the LR space to the high-resolution (HR) space, an auxiliary module which maps the SR results back to the degraded LR images provides additional constraint. In the second stage, the multi-scale features produced by the detection heads are further enhanced by the lightweight feature adaptation modules, which aim to further bridge the gap between the SR result and the corresponding HR image. During training, the detector is kept frozen in our framework, leading to a flexible plug-and-play mechanism. Experiments demonstrate that our approach achieves better performance on LR images than many state-of-the-art methods. To facilitate further study, our source code will be available at: https://***/Zijian-Yuan/TSE-YOLO.

关键词： Training Upper bound Head Accuracy Source coding Superresolution Detectors

Soccer match broadcast video analysis method based on detection and tracking

学校读者我要写书评

暂无评论

Soccer match broadcast video analysis method based on detect...

作者： Li, Hongyu Yang, Meng Yang, Chao Kang, Jianglang Suo, Xiang Meng, Weiliang Li, Zhen Mao, Lijuan Sheng, Bin Qi, Jun School of Information science and Technology Beijing Forestry University Beijing China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration Beijing China School of Athletic Performance Shanghai University of Sport Shanghai China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong Univerity Shanghai China Department of Computing Xi'an JiaoTong-Liverpool University Suzhou China

We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the (Formula presented.) of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations. © 2024 John Wiley & Sons Ltd.

关键词： Visualization