检索结果-内蒙古大学图书馆

NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Mingwu Zhang, Haiyu Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Realistic face rendering from multi-view images is beneficial to various computer vision and graphics applications. Due to the complex spatially-varying reflectance properties and geometry characteristics of faces, however, it remains challenging to recover 3D facial representations both faithfully and efficiently in the current studies. This paper presents a novel 3D face rendering model, namely Neu-Face, to learn accurate and physically-meaningful underlying 3D representations by neural rendering techniques. It naturally incorporates the neural BRDFs into physically based rendering, capturing sophisticated facial geometry and appearance clues in a collab.rative manner. Specifically, we introduce an approximated BRDF integration and a simple yet new low-rank prior, which effectively lower the ambiguities and boost the performance of the facial BRDFs. Extensive experiments demonstrate the superiority of Neu-Face in human face rendering, along with a decent generalization ability to common objects. Code is released at NeuFace. Copyright © 2023, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

Personalized Federated Learning System Based on Permissioned Blockchain

学校读者我要写书评

暂无评论

Personalized Federated Learning System Based on Permissioned...

International Conference on Intelligent Computing, Automation and Systems (ICICAS)

作者： Bo Yuan Wangjie Qiu School of Computer Science and Engineering State Key Laboratory of Software Development Environment Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China

ISBN: (纸本)9781665428118

Federated learning ensures the privacy of data generated by large-scale IoT devices. Existing federated learning frameworks, based on centralized model coordinators, still face serious security challenges such as single point of failure and lack of privacy. In this paper, we propose a personalized federated learning system based on permissioned blockchain, which is divided into four layers of architecture are IoT device layer, network layer, edge computing layer, blockchain layer, and application layer, using permissioned blockchain as a federated learning server. And a permission blockchain-based personalized federation learning algorithm is proposed, which can achieve privacy protection and resistance to poisoning attacks with high accuracy. The experimental results revealed that the system has high privacy protection and anti-poisoning attack capability and can be deployed in edge computing situations.

关键词： Resistance Privacy Data privacy computer architecture Collab.rative work Blockchains Servers

Cdga: A GAN-based Controllab.e Domain Generation Algorithm

学校读者我要写书评

暂无评论

Cdga: A GAN-based Controllable Domain Generation Algorithm

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： You Zhai Jian Yang Zixiang Wang Longtao He Liqun Yang Zhoujun Li State Key Lab of Software Development Environment Beihang University National Computer Network Emergency Response Technical Team Coordination Center of China School of Cyber Science and Technology Beihang University

Recently Command and Control (C&C) servers have attracted considerable attention in botnets and domain generation algorithms (DGAs) further enhance the stealth of C&C servers. However, Algorithmically Generated Domains (AGDs) generated by DGAs can be easily detected by previous DGA detection approaches. More specifically, the previous DGAs are hard to satisfy domain name rules, low repetition rate, and anti-detection in practical scenarios simultaneously. Designing an outstanding DGA has become a crucial issue from the botnet owner’s perspective. To mitigate these problems, we propose Cdga, a Controllab.e DGA via Generative Adversarial Networks (GAN), which is a popular backbone model for text generation in the natural language processing (NLP) *** text generation approaches are adopted by Cdga to ensure no repetition in the generated domain names and compliance with the domain rules. In addition to cheating DGA detectors, GANs are exploited to equip Cdga with a powerful anti-detection ability. Furthermore, our proposed method uses the technique of NLP to force the AGDs to meet language rules, where the generated domain names are difficult for recognition by human. By utilizing the time-dependent seed, Cdga can dynamically generate domain names, ensuring that the malware can connect to the C&C server conditioned on a specific time stamp. Experimental results demonstrate that the domain names generated by our method are realistic enough to be resistant to the state-of-the-art DGA detectors.

关键词： Command and control systems Privacy Botnet Force Detectors Generative adversarial networks Natural language processing

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Jingyuan Wu, Yufan Li, Mingxuan Lin, Xin Wu, Junjie Li, Chao MOE Engineering Research Center of ACAT School of Computer Science Engineering Beihang University China Beijing Key Laboratory of ESSTCO School of Economics and Management Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China

While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks. Tremendous research efforts have been dedicated to mitigating the threats of adversarial attacks, but the essential trait of adversarial examples is not yet clear, and most existing methods are yet vulnerable to hybrid attacks and suffer from counterattacks. In light of this, in this paper, we first reveal a gradient-based correlation between sensitivity analysis-based DNN interpreters and the generation process of adversarial examples, which indicates the Achilles's heel of adversarial attacks and sheds light on linking together the two long-standing challenges of DNN: fragility and unexplainability. We then propose an interpreter-based ensemble framework called X-Ensemble for robust adversary defense. X-Ensemble adopts a novel detection-rectification process and features in building multiple sub-detectors and a rectifier upon various types of interpretation information toward target classifiers. Moreover, X-Ensemble employs the Random Forests (RF) model to combine sub-detectors into an ensemble detector for adversarial hybrid attacks defense. The non-differentiable property of RF further makes it a precious choice against the counterattack of adversaries. Extensive experiments under various types of state-of-the-art attacks and diverse attack scenarios demonstrate the advantages of X-Ensemble to competitive baseline methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Application of Blockchain Based on Fabric Consensus Network Model in Secure Encryption of Educational Information

学校读者我要写书评

暂无评论

Applied Mathematics and Nonlinear sciences 2024年第1期9卷

作者： Yuan, Bo Wu, Faguo School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing100191 China

This paper combines blockchain technology with an information encryption algorithm to design a blockchain-based educational information protection model. It focuses on the role of Fabric architecture and blockchain data structure for information security protection. A chaotic cipher is used to encrypt the information, combined with the iteration of nonlinear functions to generate pseudo-random numbers to realize the unpredictability of the information. Using symbolic dynamics to obtain the control parameter or initial value of the chaotic mapping, combining the sequence of symbols to solve for another value, and finally presenting it in the form of ciphertext in the client for the data accessor to query and access the data. The effectiveness and practicality of educational information security encryption are examined by applying the model of constructed information protection. The results show that the response time of the blockchain module changes depending on the information, and the response time is basically maintained between 2.2 seconds and 2.4 seconds, which is in a reasonable range. In educational information security defense, the information protection model is able to effectively defend the network against attacks, with the highest number of attacks against the attack named external, with the highest number close to 50 million. © 2023 Bo Yuan et al., published by Sciendo.

关键词： Cryptography

Incremental Measurement of Structural Entropy for Dynamic Graphs

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Runze Peng, Hao Liu, Chunyang Li, Angsheng State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China School of Cyber Science and Technology Beihang University Beijing100191 China Didi Chuxing Beijing100193 China

Structural entropy is a metric that measures the amount of information embedded in graph structure data under a strategy of hierarchical abstracting. To measure the structural entropy of a dynamic graph, we need to decode the optimal encoding tree corresponding to the best community partitioning for each snapshot. However, the current methods do not support dynamic encoding tree updating and incremental structural entropy computation. To address this issue, we propose Incre-2dSE, a novel incremental measurement framework that dynamically adjusts the community partitioning and efficiently computes the updated structural entropy for each updated graph. Specifically, Incre-2dSE includes incremental algorithms based on two dynamic adjustment strategies for two-dimensional encoding trees, i.e., the naive adjustment strategy and the node-shifting adjustment strategy, which support theoretical analysis of updated structural entropy and incrementally optimize community partitioning towards a lower structural entropy. We conduct extensive experiments on 3 artificial datasets generated by Hawkes Process and 3 real-world datasets. Experimental results confirm that our incremental algorithms effectively capture the dynamic evolution of the communities, reduce time consumption, and provide great interpretability. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

Ethical Principles and Governance Technology development of AI in China

学校读者我要写书评

暂无评论

engineering 2020年第3期6卷 302-309页

作者： Wenjun Wu Tiejun Huang Ke Gong State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Chinese Institute of New Generation Artificial Intelligence Development Strategie Nankai UniversityTianjin 300071China

Ethics and governance are vital to the healthy and sustainable development of artificial intelligence(AI).With the long-term goal of keeping AI beneficial to human society,governments,research organizations,and companies in China have published ethical guidelines and principles for AI,and have launched projects to develop AI governance *** paper presents a survey of these efforts and highlights the preliminary outcomes in *** also describes the major research challenges in AI governance research and discusses future research directions.

关键词： AI ethical principles AI governance technology Machine learning Privacy Safety Fairness

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

Rethinking Disentanglement in Unsupervised Domain Adaptation for Medical Image Segmentation

学校读者我要写书评

暂无评论

Rethinking Disentanglement in Unsupervised Domain Adaptation...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yan Wang Yixin Chen Yingying Zhang Haogang Zhu School of Instrumentation and Optoelectronic Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China BioMind Technology Zhongguancun Medical Engineering Center Beijing China School of Biological Science and Medical Engineering Beihang University Beijing China Blockchain Lab. Xiong’An Intelligent City Innovation Federation China

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shifts, especially for medical image analysis. Previous DA methods mainly focus on disentangling domain features. However, it is based on feature independence, which often can not be guaranteed in reality. In this work, we present a new DA approach called Dimension-based Disentangled Dilated Domain Adaptation (D 4 A) to disentangle the storage locations between the features to tackle the problem of domain shift for medical image segmentation tasks without the annotations of the target domain. We use Adaptive Instance Normalization (AdaIN) to encourage the content information to be stored in the spatial dimension, and the style information to be stored in the channel dimension. In addition, we apply dilated convolution to preserve anatomical information avoiding the loss of information due to downsampling. We validate the proposed method for cross-modality medical image segmentation tasks on two public datasets, and the comparison experiments and ablation studies demonstrate the effectiveness of our method, which outperforms the state-of-the-art methods.

关键词：