检索结果-内蒙古大学图书馆

Pcas: An Improved Pairing-Free Certificateless Aggregate Signature with Conditional Privacy Preserving for Vanets

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Gong, Ziyan Gao, Tianhan Guo, Nan School of Software Engineering Northeastern University Shenyang110167 China School of Computer Science And Engineering Northeastern University Shenyang110167 China

Due to the rapid topology changes, a large amount of data exchange is generated in large-scale, and variable-density vehicular ad-hoc networks (VANETs). Therefore, vehicle communication security becomes the most critical aspect of road traffic. It is extremely difficult to design protocols for vehicle authentication that satisfy the security and privacy requirements while still providing efficient communication. With the certificateless aggregate signature (CLAS) scheme, the key escrow problem based on identity signature is solved. Thus, some new CLAS mechanisms have been proposed for the authentication in VANETs. However, many flaws, such as the high computational overhead and malicious KGC attack, are still existed in most CLAS schemes. In this paper, we first review a newly proposed CLAS scheme, and give an analysis of the existing issues. Afterwards, we give an enhanced CLAS scheme and apply it to vehicle authentication in VANETs. The security of the scheme is proved under the random oracle security model. Moreover, through theoretical analysis and simulation, the proposed scheme is shown to own better transmission overhead and computation overhead compared with the literature ones. © 2022, The Authors. All rights reserved.

关键词： Vehicular ad hoc networks

Unsupervised Recognition of Unknown Objects for Open-World Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fang, Ruohuan Pang, Guansong Zhou, Lei Bai, Xiao Zheng, Jin School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University Singapore School of Computer Science and Artificial Intelligence Wuhan University of Technology China

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets. Code is available at https://***/frh23333/mepu-owod. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

CEGRL-TKGR: A Causal Enhanced Graph Representation Learning Framework for Temporal Knowledge Graph Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Jinze Sheng, Yongpan He, Lirong Qin, Yongbin Liu, Ming Jia, Tao College of Computer and Information Science Southwest University Chongqing400715 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China School of Information Science and Engineering Chongqing Jiaotong University Chongqing400074 China College of Computer Science and Technology The State Key Laboratory of Public Big Data Guizhou University China Deakin University VIC3125 Australia

Temporal knowledge graph reasoning (TKGR) is increasingly gaining attention for its ability to extrapolate new events from historical data, thereby enriching the inherently incomplete temporal knowledge graphs. Existing graph-based representation learning frameworks have made significant strides in developing evolving representations for both entities and relational embeddings. Despite these achievements, there’s a notable tendency in these models to inadvertently learn biased data representations and mine spurious correlations, consequently failing to discern the causal relationships between events. This often leads to incorrect predictions based on these false correlations. To address this, we propose an innovative Causal Enhanced Graph Representation Learning framework for TKGR (named CEGRL-TKGR). This framework introduces causal structures in graph-based representation learning to unveil the essential causal relationships between events, ultimately enhancing the performance of the TKGR task. Specifically, we first disentangle the evolutionary representations of entities and relations in a temporal knowledge graph sequence into two distinct components, namely causal representations and confounding representations. Then, drawing on causal intervention theory, we advocate the utilization of causal representations for predictions, aiming to mitigate the effects of erroneous correlations caused by confounding features, thus achieving more robust and accurate predictions. Finally, extensive experimental results on six benchmark datasets demonstrate the superior performance of our model in the link prediction task. © 2024, CC BY.

关键词： Spatio-temporal data

A One-Dimensional Residual Network and Physical Fitness-Based Exercise Prescription Recommendation Method

学校读者我要写书评

暂无评论

A One-Dimensional Residual Network and Physical Fitness-Base...

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Runqing Fan Zhenlian Peng Buqing Cao Jianxun Liu Peng Che Tieping Chen School of Computer Science and Engineering Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China School of Physical Education Hunan University of Science and Technology Xiangtan China

In the context of the national big data strategy, physical fitness test data has become one of the main influencing factors in guiding and promoting the participation of the population in sports and fitness. Recommending exercise prescriptions based on national physical fitness test data has become an important research topic. However, currently, there is little research on how to accurately use computer data processing technology to recommend exercise prescriptions based on physical fitness test data. In this study, we propose a ResNet-based Exercise Prescription (ResNet-EP) method that utilizes one-dimensional residual neural network technology to recommend exercise prescriptions based on physical fitness testing data. This method comprehensively analyzes physical fitness testing data and exercise prescription data and realizes the automatic recommendation of exercise prescriptions. Experimental results on a real dataset demonstrate that the ResNet-EP model outperforms other comparison models in terms of precision (79.98%), recall (83.73%), and F1 score (81.81%). This study provides novel insights into the combination of physical fitness testing and exercise.

关键词：

Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Hongyu Zhang, Jing Hui, Tianrui Ma, Bin Ding, Zihan Wei, Xiaoming Han, Jizhong Liu, Si School of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Meituan Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous discriminative methods achieve only weak or coarse-grained alignment by panoptic segmentation pretraining or CLIP model adaptation. Given the recent progress of text-to-image Diffusion models, several works have shown their capability to achieve fine-grained image-text alignment through cross-attention maps and improved general segmentation performance. However, the direct use of phrase features as static prompts to apply frozen Diffusion models to the PNG task still suffers from a large task gap and insufficient vision-language interaction, yielding inferior performance. Therefore, we propose an Extractive-Injective Phrase Adapter (EIPA) bypass within the Diffusion UNet to dynamically update phrase prompts with image features and inject the multimodal cues back, which leverages the fine-grained image-text alignment capability of Diffusion models more sufficiently. In addition, we also design a Multi-Level Mutual Aggregation (MLMA) module to reciprocally fuse multi-level image and phrase features for segmentation refinement. Extensive experiments on the PNG benchmark show that our method achieves new state-of-the-art performance. © 2024, CC BY-NC-ND.

关键词： Image segmentation

Personalized Federated Learning for Generative AI-Assisted Semantic Communications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Yubo Jiang, Feibo Dong, Li Wang, Kezhi Yang, Kun School of Intelligent Software and Engineering Nanjing University Suzhou China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China Department of Computer Science Brunel University London United Kingdom

Semantic Communication (SC) focuses on transmitting only the semantic information rather than the raw data. This approach offers an efficient solution to the issue of spectrum resource utilization caused by the various intelligent applications on Mobile Users (MUs). Generative Artificial Intelligence (GAI) models have recently exhibited remarkable content generation and signal processing capabilities, presenting new opportunities for enhancing SC. Therefore, we propose a GAI-assisted SC (GSC) model deployed between MUs and the Base Station (BS). Then, to train the GSC model using the local data of MUs while ensuring privacy and accommodating heterogeneous requirements of MUs, we introduce Personalized Semantic Federated Learning (PSFL). This approach incorporates a novel Personalized Local Distillation (PLD) and Adaptive Global Pruning (AGP). In PLD, each MU selects a personalized GSC model as a mentor tailored to its local resources and a unified Convolutional Neural Networks (CNN)-based SC (CSC) model as a student. This mentor model is then distilled into the student model for global aggregation. In AGP, we perform network pruning on the aggregated global model according to real-time communication environments, reducing communication energy. Finally, numerical results demonstrate the feasibility and efficiency of the proposed PSFL scheme. © 2024, CC BY-NC-ND.

关键词： Federated learning

Deep Learning in Automatic Recognition of Mongolian Compound Nouns

学校读者我要写书评

暂无评论

Deep Learning in Automatic Recognition of Mongolian Compound...

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Ha Si Du La Yang Ding College of Computer Science and Information Engineering Hohhot Minzu College Hohhot China College of Computer Science and Technology Inner Mongolia Normal University Hohhot China School of Software and Big Data Inner Mongolia Electronic Information Vocational Technical College Hohhot China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

Mongolian compound nouns often become the vehicle for the creation of new concepts and terms due to their diverse combinations and flexible expressive power. In the field of natural language shallow syntactic analysis, the recognition of Mongolian compound nouns plays an important role, and its performance will directly affect the processing effect of related research. In the current academic research, the research on automatic recognition of Mongolian compound nouns is still insufficient, especially in the automatic recognition of Mongolian compound nouns using deep learning technology, which is almost in a blank state. In this study, we firstly construct a Mongolian compound noun annotated corpus, and on the basis of the constructed annotated corpus, we propose a Mongolian compound noun automatic recognition model based on deep learning for the fact that there is no deep learning method for recognising Mongolian compound nouns at present. The model takes Conditional Random Field (CRF) as the basic framework to make full use of contextual information by considering the joint probability distribution of the whole sequence. During the model construction process, the TextCNN model is incorporated and by designing a multi-scale convolutional kernel, the model is able to effectively capture the local features of Mongolian compound nouns. The experimental results show that the automatic Mongolian compound noun recognition model based on deep learning proposed in this study performs well on the Mongolian compound noun recognition task, with an F1 value of 93.40%.

关键词： Deep learning Natural languages Syntactics Conditional random fields Probability distribution Pattern recognition Compounds Kernel Context modeling

Multi-Objective Fine-Tuning for Enhanced Program Repair with LLMs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Boyang Tian, Haoye Ren, Jiadong Zhang, Hongyu Klein, Jacques Bissyandé, Tegawendé F. Le Goues, Claire Jin, Shunfu School of Information Science and Engineering Yanshan University China Jisuan Institute of Technology Beijing JudaoYouda Network Technology Co. Ltd. China School of Computer Science Carnegie Mellon University United States SnT University of Luxembourg Luxembourg School of Big Data and Software Engineering Chongqing University China

Large language models (LLMs) have demonstrated remarkable capabilities on a broad spectrum of downstream tasks. Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks are however generally overlooking the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MOREPAIR, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective 1), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective 2). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality patches. We apply MOREPAIR to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on C++ and Java repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 7.6% to 10% in Top-10 repair suggestions. We further show that our fine-tuning strategy yields superior performance compared to the incumbent state-of-the-art in fine-tuned models for program repair, Fine-tune-CoT and RepairLLaMA. Copyright © 2024, The Authors. All rights reserved.

关键词： Repair

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wan, Yuanyu Wei, Tong Xue, Bo Song, Mingli Zhang, Lijun School of Software Technology Zhejiang University Ningbo China State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering Southeast University Nanjing China Department of Computer Science City University of Hong Kong Hong Kong National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China

We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using only local computations and communications. Previous studies have established O(n5/4ρ−1/2√T) and O(n3/2ρ−1 log T) regret bounds for convex and strongly convex functions respectively, where n is the number of local learners, ρ √T) for convex functions and Ω(n) for strongly convex functions. To fill these gaps, in this paper, we first develop a novel D-OCO algorithm that can respectively reduce the regret bounds for convex and strongly convex functions to Õ(nρ−1/4√T) and Õ(nρ−1/2 log T). The primary technique is to design an online accelerated gossip strategy that enjoys a faster average consensus among local learners. Furthermore, by carefully exploiting spectral properties of a specific network topology, we enhance the lower bounds for convex and strongly convex functions to Ω(nρ−1/4√T) and Ω(nρ−1/2 log T), respectively. These results suggest that the regret of our algorithm is nearly optimal in terms of T, n, and ρ for both convex and strongly convex functions. Finally, we propose a projection-free variant of our algorithm to efficiently handle practical applications with complex constraints. Our analysis reveals that the projection-free variant can achieve O(nT 3/4) and O(nT 2/3(log_ T)1/3) regret bounds for convex and strongly convex functions with nearly optimal Õ(ρ−1/2√T) and Õ(ρ−1/2T 1/3(log T)2/3) communication rounds, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization algorithms