检索结果-内蒙古大学图书馆

LAS-AT: Adversarial Training with Learnable Attack Strategy

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jia, Xiaojun Zhang, Yong Wu, Baoyuan Ma, Ke Wang, Jue Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyberspace Security University of Chinese Academy of Sciences Beijing China Tencent AI Lab Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient Decent (PGD) with manually specifying attack parameters for AE generation. A combination of the attack parameters can be referred to as an attack strategy. Several works have revealed that using a fixed attack strategy to generate AEs during the whole training phase limits the model robustness and propose to exploit different attack strategies at different training stages to improve robustness. But those multi-stage hand-crafted attack strategies need much domain expertise, and the robustness improvement is limited. In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness. Our framework is composed of a target network that uses AEs for training to improve robustness, and a strategy network that produces attack strategies to control the AE generation. Experimental evaluations on three benchmark databases demonstrate the superiority of the proposed method. The code is released at https://***/jiaxiaojunQAQ/LAS-AT. Copyright © 2022, The Authors. All rights reserved.

关键词： Cryptography

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hao, Yanbin Wang, Shuo Cao, Pei Gao, Xinjian Xu, Tong Wu, Jinmeng He, Xiangnan The CCCD Key Lab of Ministry of Culture and Tourism School of Data Science School of Information Science and Technology University of Science and Technology of China Anhui 230026 China The Wuhan Research Institute of Posts and Telecommunications Hubei Wuhan430205 China The School of Computer Science and Information Engineering School of Artificial Intelligence Hefei University of Technology Anhui 230009 China The School of Data Science School of Computer Science and Technology University of Science and Technology of China Anhui 230026 China The Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Hubei Wuhan430070 China

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ( Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Artificial Bee Colony Algorithm Combined with Uniform Design 15th

学校读者我要写书评

暂无评论

Artificial Bee Colony Algorithm Combined with Uniform Design

15th International Conference on Intelligent information Hiding and Multimedia Signal Processing, IIH-MSP 2019, held in conjunction with the 12th International Conference on Frontiers of information Technology, Applications and Tools, FITAT 2019

作者： Zhang, Jie Feng, Junhong Chen, Guoqiang Yang, Xiani School of Computer Science and Engineering Guangxi Universities Key Lab of Complex System Optimization and Big Data Processing Yulin Normal University YulinGuangxi537000 China School of Computer and Information Engineering Henan University KaifengHenan475004 China

ISBN: (纸本)9789811397097

As artificial bee colony algorithm is sensitive to the initial solutions, and is easy to fall into local optimum and premature convergence, this study presents a novel artificial bee colony algorithm based on uniform design to acquire the better initial solutions. It introduces an initialization method with uniform design to replace random initialization, and selects the better ones of those initial bees generated by the initialization method as the initial bee colony. This study also introduces a crossover operator based on uniform design, which can search evenly the solutions in the small vector space formed by two parents. This can increase searching efficiency and accuracy. The best two of the offsprings generated by the crossover operator based on uniform design are taken as new offsprings, and they are compared with their parents to determine whether to update their patents or not. The crossover operator can ensure that the proposed algorithm searches uniformly the solution space. Experimental results performed on several frequently used test functions demonstrate that the proposed algorithm has more outstanding performance and better global searching ability than standard artificial bee colony algorithm. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Vector spaces

Awareness requirement and performance management for adaptive systems: a survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rashid, Tarik A. Hassan, Bryar A. Alsadoon, Abeer Qader, Shko Vimal, S. Chhabra, Amit Yaseen, Zaher Mundher Computer Science and Engineering Department School of Science and Engineering University of Kurdistan Hewler Kurdistan Region Erbil Iraq Department of Information Technology Kurdistan Institution for Strategic Studies and Scientifc Research KRI Sulaymaniyah46001 Iraq School of Computing and Mathematics Charles Sturt University Sydney Australia School of Computing Engineering and Mathematics Western Sydney University Sydney City Campus Sydney Australia Sydney Australia Information Technology Department Kent Institute Australia Sydney Australia Department of Information Technology University College of Goizha Kurdistan Region Sulaimani Iraq Data Analytics Lab Department of Artifcial Intelligence and Data Science Ramco Institute of Technology North Venganallur Village Virudhunagar District Tamilnadu Rajapalayam626 117 India Department of Computer Engineering and Technology Guru Nanak Dev University Amritsar India Civil and Environmental Engineering Department King Fahd University of Petroleum & Minerals Dhahran31621 Saudi Arabia Department of Computer Science College of Science Charmo University KRI Chamchamal46023 Iraq Department of Information Technology Computer Science Institute Sulaimani Polytechnic University KRI Sulaymaniyah46001 Iraq

Self-adaptive software can assess and modify its behavior when the assessment indicates that the program is not performing as intended or when improved functionality or performance is available. Since the mid-1960s, the subject of system adaptivity has been extensively researched, and during the last decade, many application areas and technologies involving self-adaptation have gained prominence. All of these efforts have in common the introduction of self-adaptability through software. Thus, it is essential to investigate systematic software engineering methods to create self-adaptive systems that may be used across different domains. The primary objective of this research is to summarize current advances in awareness requirements for adaptive strategies based on an examination of state-of-the-art methods described in the literature. This paper presents a review of self-adaptive systems in the context of requirement awareness and summarizes the most common methodologies applied. At first glance, it gives a review of the previous surveys and works about self-adaptive systems. Afterward, it classifies the current self-adaptive systems based on six criteria. Then, it presents and evaluates the most common self-adaptive approaches. Lastly, an evaluation among the self-adaptive models is conducted based on four concepts (requirements description, monitoring, relationship, dependency/impact, and tools). © 2023, CC BY-NC-ND.

关键词： Adaptive systems

An Efficient and Reliable Asynchronous Federated Learning Scheme for Smart Public Transportation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Chenhao Qu, Youyang Luan, Tom H. Eklund, Peter W. Xiang, Yong Gao, Longxiang The Deakin Blockchain Innovation Lab School of Information Technology Deakin University Geelong Australia Data 61 Australia Commonwealth Scientific and Industrial Research Organization Australia School of Cyber Engineering Xidian University Shaanxi China School of Information Technology Deakin University Geelong Australia Qilu University of Technology Shandong Computer Science Center China

Since the traffic conditions change over time, machine learning models that predict traffic flows must be updated continuously and efficiently in smart public transportation. Federated learning (FL) is a distributed machine learning scheme that allows buses to receive model updates without waiting for model training on the cloud. However, FL is vulnerable to poisoning or DDoS attacks since buses travel in public. Some work introduces blockchain to improve reliability, but the additional latency from the consensus process reduces the efficiency of FL. Asynchronous Federated Learning (AFL) is a scheme that reduces the latency of aggregation to improve efficiency, but the learning performance is unstable due to unreasonably weighted local models. To address the above challenges, this paper offers a blockchain-based asynchronous federated learning scheme with a dynamic scaling factor (DBAFL). Specifically, the novel committee-based consensus algorithm for blockchain improves reliability at the lowest possible cost of time. Meanwhile, the devised dynamic scaling factor allows AFL to assign reasonable weights to stale local models. Extensive experiments conducted on heterogeneous devices validate outperformed learning performance, efficiency, and reliability of DBAFL. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean label

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Shengshan Zhou, Ziqi Zhang, Yechao Zhang, Leo Yu Zheng, Yifeng He, Yuanyuan Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Information Technology Deakin University VIC3216 Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 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 HUST Wuhan430074 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they also cannot meet the intrinsic demand of image retrieval backdoor. In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. Specifically, we first propose a new conditional generative adversarial network (cGAN) pipeline to effectively generate poisoned samples. For any given benign image, it seeks to generate a natural-looking poisoned counterpart with a unique invisible trigger. In order to improve the attack effectiveness, we introduce a label-based contrastive learning network labCLN to exploit the semantic characteristics of different labels, which are subsequently used for confusing and misleading the target model to learn the embedded trigger. We finally explore the mechanism of backdoor attacks on image retrieval in the hash space. Extensive experiments on multiple benchmark datasets verify that BadHash can generate imperceptible poisoned samples with strong attack ability and transferability over state-of-the-art deep hashing schemes. © 2022, CC BY.

关键词： Deep neural networks

Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation

学校读者我要写书评

暂无评论

Heterogeneous Graph Neural Network for Privacy-Preserving Re...

IEEE International Conference on data Mining (ICDM)

作者： Yuecen Wei Xingcheng Fu Qingyun Sun Hao Peng Jia Wu Jinyan Wang Xianxian Li Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computing Macquarie University Sydney Australia

Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.

关键词： Training Privacy Differential privacy Social networking (online) Graph neural networks Topology Resource management

Model-enhanced Vector Index

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wei, Yuecen Fu, Xingcheng Sun, Qingyun Peng, Hao Wu, Jia Wang, Jinyan Li, Xianxian Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computing Macquarie University Sydney Australia

关键词： Budget control