检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Lan Wu Quan Liu Lihua Zhang Zhigang Huang School of Computer Science and Technology Soochow University Soochow China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China

Offline reinforcement learning is an approach for transforming static datasets into powerful decision engines. It cannot interact with the environment online, which leads to distribution shifts. Previous approaches addressed this problem by making the current policy as close as possible to the behavior policy. However, this type of approach severely limits the generalization ability of Q-functions. To address the above concerns, offline reinforcement learning with policy guidance and uncertainty estimation (PGUE) is proposed. PGUE proposes a fine-grained adjustment approach that improves the generalization ability of Q-functions using a perturbation model. The enhancement of the out-of-distribution generalization of Q-functions is achieved through the implicit guidance of the state space via a deterministic latent policy. Meanwhile, integrating uncertainty estimation into the loss function improves the in-distribution generalization of Q-functions. On the D4RL benchmark, PGUE has better performance than baselines. Moreover, we verify the state distribution and its out-of-distribution generalization ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Offline Reinforcement Learning with Generative Adversarial Networks and Uncertainty Estimation

Offline Reinforcement Learning with Generative Adversarial N...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

In recent years, offline reinforcement learning has attracted considerable attention in artificial intelligence. By generating a static dataset through a behavior policy, it is unable to engage in online interactions with the environment. However, this inevitably leads to states or actions undergoing inherent distribution shifts. To address the above concerns, offline reinforcement learning with generative adversarial networks and uncertainty estimation (GANUE) is proposed. This approach parameterizes the conditional generative adversarial networks and avoids the over-constraint problem that would be introduced when using a distance metric. Estimating the Q-value through ensemble uncertainty not only relaxes the policy constraint strength but also enhances the out-of-distribution generalization ability. The experimental results show that GANUE significantly performs better on the Maze2D and Adroit tasks than multiple baselines. In addition, we perform sensitivity analysis experiments for the parameters of the perturbation model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Policy-Controlled Signature Scheme for end-to-end Secure Communication 12

A Policy-Controlled Signature Scheme for end-to-end Secure C...

引用

12th International Conference on Advanced Cloud and Big Data, CBD 2024

作者： Yu, Feng Meng, Linghui Xi, Jing Li, Xianxian Lu, Qianhui Zhu, Weidong Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology GuiLin China University of SouthEast Jiangsu Provincial Key Laboratory of Netwrok and Information Security Nanjing China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security GuiLin China Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing Guangxi Normal University GuiLin China

ISBN: (纸本)9798331511074

In the digitalized society, end-to-end security communication is receiving increasing attention. Issues such as ma-licious sender impersonation and over-privilege communication continue to prevail in end-to-end communication. This paper pro-poses a policy-controlled signature scheme aimed at addressing these concerns through identity verification and permission man-agement, thus establishing a secure mode of communication. The scheme designs policy-controlled signatures with partial policy hiding functionality, employing expressive access structures and garbled Bloom Filter (GBF) to protect the sender's attributes. In comparison to related approaches, this scheme provides benefits in terms of signature computation cost, thereby enhancing the resilience and efficiency of the communication system against attacks. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A New Approach of Intrusion Detection with Command Sequence-To-Sequence Model 6th

A New Approach of Intrusion Detection with Command Sequence-...

引用

6th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2019

作者： Liu, Wei Mao, Yu Ci, Linlin Zhang, Fuquan School of Computer Science and Technology Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350117 China

ISBN: (纸本)9789811650352

Traditionally, researchers have focused on network level intrusion detection and program level intrusion detection to improve computer security. However, neither approach is foolproof. We argue that the internal and external security of a computer system are equally important. Typically, a successful attacker manifests in the form of the attacker becoming a user on the host either with elevated or normal user privileges. At this point, user-level intrusion detection attempts to deter and curtail an attacker even after the system has been compromised. In this work, we introduce a new approach of intrusion detection based on recurrent neural networks (RNNs) to solve the long sequential problem. We build a robust user command sequence-to-sequence model by semantic modeling command. Our model implements the prediction of user command sequence and the prophesying of user behaviors. The experimental results on data sets of Purdue University, SEA and self-collected data show that an accurate, effective and efficient detection can be achieved by using the proposed approach. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient fully analytical polygon-based continuous shading rendering CGH algorithm with specular reflection 14

Efficient fully analytical polygon-based continuous shading ...

引用

Holography, Diffractive Optics, and Applications XIV 2024

作者： Wang, Pin Fu, Qingyang Zhang, Yaping Poon, Ting-Chung Yunnan Provincial Key Laboratory of Modern Information Optics Kunming University of Science and Technology Kunming Yunnan650500 China Nanjing University of Science and Technology Nanjing Jiangsu210094 China Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States

ISBN: (纸本)9781510682085

The fully analytical method has been widely studied for its higher accuracy and efficiency, and the addition of shading rendering can effectively improve the three-dimensional perception of reconstructed images. However, existing fully analytical polygon-based shading rendering methods suffer from high computational complexity and complexity due to the need for additional calculation of the highlight spectrum. Based on previous research, we employ a continuous light and shadow algorithm that uses linear interpolation to decouple the reflection term from the spectrum, meaning that we incorporate the specular component into the calculation of vertex modulus, and separately compute the vertex modulus and the corresponding spectrum values, simplifying the calculation process of existing Blinn Phong lighting models. The algorithm can effectively generate highly realistic holographically reconstructed images with high gloss effects under continuous illumination. It achieves computational efficiency than existing algorithms, without increasing the number of polygons. Simulations and experimental results have verified the effectiveness of our proposed method. © 2024 SPIE. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Learnable Graph Augmentation 48

Graph Contrastive Learning with Learnable Graph Augmentation

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Pu, Xinyan Zhang, Ke Shu, Huazhong Coatrieux, Jean Louis Kong, Youyong Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Nanjing China Universit de Rennes 1 Ltsi Rennes France Centre de Recherche en Information BioMdicale Sino-Franais Rennes France

ISBN: (纸本)9781728163277

Graph contrastive learning has gained popularity due to its success in self-supervised graph representation learning. Augmented views in contrastive learning greatly determine the quality of the learned representations. Handcrafted data augmentations in previous work require tedious trial-and- errors per dataset, which is time-consuming and resource-intensive. Here, we propose a Graph Contrastive learning framework with Learnable graph Augmentation called GraphCLA. Specifically, learnable graph augmentation trains augmented views by minimizing the mutual information (MI) between the input graphs and their augmented graphs. This paper designs a kernel contrastive loss function based on an end-to-end differentiable graph kernel to learn augmented views. In addition, this paper utilizes a min-max optimization strategy to learn challenging augmented graphs and to learn discriminative representations adversarially. Finally, we compared GraphCLA with state-of-the-art self-supervised learning baselines and experimentally validate the effectiveness of GraphCLA. © 2023 IEEE.

关键词： Contrastive learning data augmentation graph representation learning

来源：评论

学校读者我要写书评

暂无评论

Dual-branch adjacent connection and channel mixing network for video crowd counting

引用

Pattern Recognition 2025年 167卷

作者： Ling, Miaogen Chen, Jixuan Liu, Yongwen Fang, Wei Geng, Xin School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China School of Computer Science and Engineering Southeast University Nanjing210096 China

This paper focuses on the problem of video crowd counting, which usually uses the spatial and temporal correlations of the consecutive frames to achieve better performance than the single-image crowd counting methods. However, most of the current video crowd counting methods either use only two or three frames for optical flow or frame-difference feature extraction or construct a single-branch network to extract spatiotemporal correlated features. The interactions of features for multiple adjacent frames, which can effectively prevent disturbances caused by background noise, are mostly overlooked. Considering the above problems, we propose a dual-branch adjacent connection and channel mixing network for multi-frame video crowd counting. For the upper branch, an adjacent layer connection method is proposed to capture the multi-scaled spatiotemporal correlations among multiple consecutive frames instead of the traditional dense connections in decomposed 3D convolutional blocks. It achieves better performance and low computation cost. For the lower branch, adaptive temporal channel mixing blocks are proposed to exchange partial channel information among the adjacent frames for feature interaction. The partial channel transpose operation is first proposed to exchange information. It is parameter-free and flexible to achieve interactions among features of any number of consecutive frames. The proposed method outperforms the current image-based and video-based crowd counting models, achieving state-of-the-art performance on six publicly available datasets. The code is available at: https://***/aaaabbbbcccccjxzxj/mfvcc. © 2025 Elsevier Ltd

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Context Modeling for Road Obstacle Detection 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Wu, Xiuen Wang, Tao Liang, Lingyu Li, Zuoyong Ching, Fum Yew College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China Guangzhou510320 China Penang11800 Malaysia

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling. Firstly, a data-driven spatial context model of the driving scene is constructed with the layouts of the training data. Then, obstacles in the input image are detected via the state-of-the-art object detection algorithms, and the results are combined with the generated scene layout. In addition, to further improve the performance and robustness, temporal information in the image sequence is taken into consideration, and the optical flow is obtained in the vicinity of the detected objects to track the obstacles across neighboring frames. Qualitative and quantitative experiments were conducted on the Small Obstacle Detection (SOD) dataset and the Lost and Found dataset. The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A New Image Encryption Strategy Based on Arnold Transformation and Logistic Map 11th

A New Image Encryption Strategy Based on Arnold Transformati...

引用

11th International Conference on computer Engineering and Networks, CENet2021

作者： Sun, Xiyu Chen, Zhong College of Computer Science and Technology Hengyang Normal University Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

ISBN: (纸本)9789811665530

Aiming at the problem of digital image encryption, an image encryption algorithm is proposed. The algorithm is divided into preparation stage and permutation diffusion stage. In the preparation stage, Arnold algorithm is improved and combined with Logistic chaotic map to generate the necessary sequence for the next stage. In the permutation diffusion stage, the final encrypted image is obtained by permutation, positive XOR operation, shift operation, S-box substitution and reverse XOR operation. The experimental results show that the algorithm can effectively resist the common attacks. For the 128 × 128 Lena gray image, the resistance performance number of pixel change rate (NPCR) is 99.6090, unified average changing intensity (UACI) is 33.4316. In addition, the time consumption of the algorithm is about 0.0055 s, and the experiments show that the algorithm has high security and real-time performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

A Stronger Leakage Model Based on Conditional Generative Adversarial Networks for Correlation Power Analysis

引用

International Journal of Circuit Theory and Applications 2025年第0期

作者： Tang, Cheng Li, Lang Ou, Yu College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hengyang China

Deep learning-based side-channel attacks (DL-SCA) have attracted widespread attention in recent years, and most of the researchers are devoted to finding the optimal DL-SCA method. At the same time, traditional SCA methods have lost their luster. However, traditional attacks still have certain advantages. Compared with the DL-SCA method, they do not require cumbersome engineering of tuning DL models and hyperparameters, making them easier to implement. Correlation power analysis (CPA), as a traditional SCA method, is still widely used in various analysis scenarios and plays an important role. In CPA, the leakage model is the key to simulating the power consumption, and it decides the attack efficiency. However, the existing leakage models are designed based on theory but ignore the actual attack scene. We found that conditional generative adversarial networks (CGAN) can ideally learn the target device's leakage characteristics and real power consumption. We let CGAN pre-learn the leakage of the target device, and then make the generator as the leakage model (Formula presented.). The (Formula presented.) leakage model can characterize the leakages of the device and consider the presence of noise in the actual scenario. It can map the power consumption more realistically and accurately, which can lead to a more powerful CPA attack. In this work, three kinds of (Formula presented.) leakage models ((Formula presented.) 1, (Formula presented.) 2, and (Formula presented.) 3 leakage models) corresponding to the labels least significant bit (LSB), hamming weight (HW), and identity (ID) of CGAN are discussed. The experimental results show that the (Formula presented.) 3 leakage model has better attack performance. Compared with the ordinary HW leakage model, the number of traces needed to recover the key on the ASCAD and SAKURA-AES datasets reduced by about 38.9% and 85.9%, respectively. © 2025 John Wiley & Sons Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：