检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Detecting Backdoors During the Inference Stage Based on Corr...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Probabilistic Siamese Visual Tracking with a Conditional Variational Autoencoder

Exploiting Probabilistic Siamese Visual Tracking with a Cond...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Wenhui Huang Jason Gu Peiyong Duan Sujuan Hou Yuanjie Zheng School of Information Science and Engineering Shandong Normal University China Dalhousie University Halifax Canada Key Lab of Intelligent Computing & Information Security in Universities of Shandong Shandong Normal University China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Shandong Normal University China

Visual tracking is a fundamental capability for robots tasked with humans and environment interaction. However, state-of-the-art visual tracking methods are still prone to failures and are imprecise when applied to challenging stereos, and their results are generally confidence agonistic. These methods depend on an embedded deep learning model to provide deterministic features or regression maps. A deterministic output with low confidence can result in disastrous consequences and lacks evidence needed for subsequent operations. Moreover, training data ambiguities or noise in the observations (so-called data uncertainty) can also lead to inherent uncertainty. In this paper, we focus on exploiting probabilistic Siamese visual tracking with a conditional variational autoencoder (CVAE). First, we build a bridge between the Siamese architecture and the CVAE and propose a novel Bayesian visual tracking method. Second, the proposed method generates a complete probability distribution that enables the production of multiple plausible tracking outputs. Third, CVAE conditioned by ground truth data encodes a low-dimensional latent space and conducts noise-injection training to prevent overfitting. Our proposed tracking method outperformed the state-of-the-art trackers on the VOT2016, VOT2018 and TColor-128 datasets.

关键词： Bridges Training Visualization Uncertainty Training data Probabilistic logic Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Multiple Feature Fusion-based Video Face Tracking for IoT Big Data

arXiv

引用

arXiv 2021年

作者： Li, Tianping Liu, Zhifeng Qiao, Jianping Key Laboratory of Medical Physics and Image Processing in Shandong Province Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Shandong Normal University School of Physics and Electronics Jinan Shandong China School of Physics and Electronics Shandong Normal University JinanShandong China School of Physics and Electronics Shandong Normal University Jinan China

With the advancement of IoT and artificial intelligence technologies, and the need for rapid application growth in fields such as security entrance control and financial business trade, facial information processing has become an important means for achieving identity authentication and information security. In this paper, we propose a multi-feature fusion algorithm based on integral histograms and a real-time update tracking particle filtering module. First, edge and colour features are extracted, weighting methods are used to weight the colour histogram and edge features to describe facial features, and fusion of colour and edge features is made adaptive by using fusion coefficients to improve face tracking reliability. Then, the integral histogram is integrated into the particle filtering algorithm to simplify the calculation steps of complex particles. Finally, the tracking window size is adjusted in real time according to the change in the average distance from the particle centre to the edge of the current model and the initial model to reduce the drift problem and achieve stable tracking with significant changes in the target dimension. The results show that the algorithm improves video tracking accuracy, simplifies particle operation complexity, improves the speed, and has good anti-interference ability and robustness. © 2021, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Classification for Mining Deeper Relationships between EEG Channels based on GCN

Epilepsy Classification for Mining Deeper Relationships betw...

引用

2020 International Conference on computer Vision, Image and Deep Learning, CVIDL 2020

作者： Chen, Xin Zheng, Yuanjie Niu, Yi Li, Chengiiang Shandong Normal University School of Information Science and Engineering Jinan250358 China Key Lab of Intelligent Computing and Information Security Universities of Shandong Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Institute of Biomedical Sciences Jinan250358 China Department of Electrical Engineering Information Technology Shandong University of Science and Technology Jinan250031 China

ISBN: (纸本)9781728194813

Epilepsy is a brain disorder caused by abnormal discharges of neurons in brain. It is one of the most commonly studied disorders in neurology. The research of epilepsy electroencephalogram (EEG) has become a hot research topic. We find that in epilepsy EEG detection task, many previous methods focused on directly collecting the data of each channel, but these methods seldom analyse relationships between signals. Therefore, we propose the Epilepsy EEG Graph Convolutional Network EGCN, which makes full use of correlations between channels to deeply mine data information. We specifically design 5-layer graph convolutional network structure for classification of healthy and epileptic patients. The method is applied to public data set (Boon and CHB-MIT) to establish a reasonable classification model. And we compare it with some advanced algorithms. The experimental results show that the E-GCN method is superior to many existing methods in classification accuracy. In brief, the E-GCN method can be effectively used in classification and detection for epilepsy. This provides new ideas for colleagues, who study epilepsy EEG. In addition, this also provides richer experience for diagnosis of epilepsy. © 2020 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Visualization of fluid simulation: An SPH-based multi-resolution method

Visualization of fluid simulation: An SPH-based multi-resolu...

引用

作者： Zhang, Guijuan Lu, Dianjie Liu, Hong School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China

Fluid simulation is an important research topic since it is widely used in virtual training, education, computer games, and digital entertainment. Generating fluid simulation results with high degree of visual realism is challenging in these applications. We present a visualization approach for fluid simulation in this paper. Our method allows students to understand the complex natural phenomena so as to solve the fluid engineering problems intuitively. In this study, an SPH (Smoothed Particle Hydrodynamics)-based multi-resolution method is proposed for fluid simulation. The method can keep the accuracy while improve the efficiency significantly. We construct a multi-resolution fluid model from bottom to top by combining fluid computation and surface reconstruction. We first compute multi-resolution particles with a novel adaptive SPH model in the bottom layer. Next, surface particles are extracted and pre-processed to provide samples for surface extraction. Then, the multi-resolution surface reconstruction model is built in the top layer. Meshes from different reconstruction resolutions are merged to obtain the final fluid surface. Experimental results show that our approach can effectively represent multi-scale fluid details and efficiently produce visual-pleasing fluid simulation results. © 2018 John Wiley & Sons, Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Reflections and Countermeasures on the Development of Secondary Vocational Teachers’ Teaching Ability Based on AI and Students’ Characteristics

Reflections and Countermeasures on the Development of Second...

引用

International Conference on Artificial Intelligence and Education (ICAIE)

作者： Lining Liu Yongsheng Zhang Penglong Zhang Wenqian Sun School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China

ISBN: (数字)9781728166599

ISBN: (纸本)9781728199207

The arrival of the era of artificial intelligence has a great impact on the produce of relationship and mode, resulting in changes in the demand for talents. As an important place to train professional and technical talents, secondary vocational schools need teachers to make changes. Teachers should improve their own educational and teaching ability, and cultivate talents of high-quality, innovative and in line with the needs of social development. By analyzing the development status of artificial intelligence in the field of education and the current students' problems facing teachers (students' characteristics), this paper gives some ideals and suggestions on the development of professional ability of secondary vocational teachers in the era of artificial intelligence.

关键词： Quality function deployment Radio frequency Education Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

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：