检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Yin, Wen Zhu, Bin Benjamin Xie, Yulai Zhou, Pan Feng, Dan School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Microsoft Corporation Beijing China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798400706868

RGB-Thermal Salient Object Detection (RGBT-SOD) plays a critical role in complex scene recognition applications, such as autonomous driving. However, security research in this domain is still in its infancy. This paper presents the first backdoor attack on RGBT-SOD systems, generating saliency maps on triggered inputs that depict non-existent salient objects chosen by the attacker or falsely mark an entire image as fully salient or entirely non-salient. We uncover that triggers have an influence range for generating non-existent salient objects, supported by a theoretical analysis. Extensive experiments show the effectiveness of our attack in both digital and physical-world scenarios. Notably, our dual-modality backdoor attack achieves an Attack Success Rate (ASR) of 86.72% with only five pairs of poisoned images in model training. After investigating potential countermeasures, we find them inadequate in mitigating our attacks, highlighting the urgent need for robust defenses against sophisticated backdoor attacks in RGBT-SOD systems. © 2024 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Destriping and Denoising with Spectral Low Rank and Tensor Nuclear Norm

Hyperspectral Image Destriping and Denoising with Spectral L...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Pengfei Liu Lanlan Liu School of Computer Science Nanjing University of Posts and Telecommunications China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing China

In this paper, we propose a new method for simultaneous hyperspectral image (HSI) destriping and denoising with spectral low-rank and tensor nuclear norm under the tensor framework. Specifically, the tensor nuclear norm is used to model the tensor low-rank property of stripe. Moreover, the nuclear norm is used to model the low-rank property of spectral gradient of HSI. Then, the ADMM algorithm is used to effectively solve the proposed model. Experimental results on simulated HSI dataset and real HSI dataset verify the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cascade Detector Based on Multi-scale Features for Small Objects in Various Backgrounds of Remote Sensing 2nd

Cascade Detector Based on Multi-scale Features for Small Obj...

引用

2nd International Conference on Image, Vision and intelligent systems, ICIVIS 2022

作者： Li, Yan Han, Shi-Yuan Xu, Tao Yang, Xiao-hui Lu, Qiu Shen, Yuan University of Jinan Jinan250022 China China High-Resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China

ISBN: (纸本)9789819909223

Different from natural images, remote sensing images in complex backgrounds have the challenges of small object feature extraction with small size, few available features, and high localization accuracy requirements. Consequently, it is difficult to detect these small objects with mainstream object detection methods. To enhance the retention of small object feature details during feature extraction and characteristics enhancement, this paper improves the Cascade R-CNN algorithm to solve the above problems of small object detection. Res2Net was used to enhance feature representation and feature fusion to extract features with fine-grained and rich semantic information. PAFPN was used for learning high-resolution features with large perceptual fields to perceive contextual information from the area around the object for inference. Cascade R-CNN was used as a high-quality detector by continuously increasing the threshold of IOU. Experiments show that the detection performance of the method proposed in this paper is 4.3% higher than that of the current mainstream deep learning methods, which is significantly better than other mainstream detection methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

BSL: Understanding and Improving Softmax Loss for Recommendation

BSL: Understanding and Improving Softmax Loss for Recommenda...

引用

International Conference on data Engineering

作者： Junkang Wu Jiawei Chen Jiancan Wu Wentao Shi Jizhi Zhang Xiang Wang MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei China The State Key Laboratory of Blockchain and Data Security Zhejiang Unversity

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement - requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://***/junkangwu/BSL.

关键词： Codes Accuracy Perturbation methods data engineering Robustness Noise measurement Proposals

来源：评论

学校读者我要写书评

暂无评论

Evaluating Consideration Level of Responses For Mental Health Chatbots

SSRN

引用

SSRN 2023年

作者： Xu, Bei Zhuang, Ziyuan Wang, Yue Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China School of Computer Science Nanjing University of Posts and Telecommunications China

Mental health chatbots are widely used and proven useful in the conversation of psychological treatments. The users of mental health chatbots require "considerate" responses because they are relatively sensitive or vulnerable. However, current mental health chatbots do not evaluate the consideration level of the responses. Current mental health chatbots generally use the categories of positive and negative to reflect consideration and sharp. This paper proposes a consideration evaluation model (CEM) to evaluate the consideration level of the responses from mental health chatbots. The experiments first prove that positive and negative cannot precisely reflect considerate and sharp, and then prove that CEM can effectively evaluate the consideration level of responses. We further use CEM to test five typical chatbots and the results indicates that some mental health chatbots may give sharp responses. © 2023, The Authors. All rights reserved.

关键词： Computational electromagnetics

来源：评论

学校读者我要写书评

暂无评论

A Causal Disentangled Multi-Granularity Graph Classification Method

arXiv

引用

arXiv 2023年

作者： Li, Yuan Liu, Li Chen, Penggang Zhang, Youmin Wang, Guoyin Chongqing Key Laboratory of Computational Intelligence China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a critical graph task, mainly relies on identifying the important substructures within the graph. At present, some graph classification methods do not combine the multi-granularity characteristics of graph data. This lack of granularity distinction in modeling leads to a conflation of key information and false correlations within the model. So, achieving the desired goal of a credible and interpretable model becomes challenging. This paper proposes a causal disentangled multi-granularity graph representation learning method (CDM-GNN) to solve this challenge. The CDM-GNN model disentangles the important substructures and bias parts within the graph from a multi-granularity perspective. The disentanglement of the CDM-GNN model reveals important and bias parts, forming the foundation for its classification task, specifically, model interpretations. The CDM-GNN model exhibits strong classification performance and generates explanatory outcomes aligning with human cognitive patterns. In order to verify the effectiveness of the model, this paper compares the three real-world datasets MUTAG, PTC, and IMDM-M. Six state-of-the-art models, namely GCN, GAT, Top-k, ASAPool, SUGAR, and SAT are employed for comparison purposes. Additionally, a qualitative analysis of the interpretation results is conducted. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Exploring tourism networks in the Guangxi mountainous area using mobility data from user generated content

引用

Journal of Mountain Science 2022年第2期19卷 322-337页

作者： LIU Yan-hua CHENG Jian-quan LYU Yu-lan School of Natural Resources and Surveying Nanning Normal UniversityNanning 530001China Department of Natural Sciences Manchester Metropolitan UniversityManchester Mi 5GDUK Joint Research Center for Urban Health and Security Intelligent Data Analytics Nanning Normal UniversityNanning 530001China School of Finance Shandong University of Finance and EconomicsJinan 250014China Shandong Key Laboratory of Blockchain Finance Jinan 250014China

Tourism-led economic growth and tourism-driven urbanization have attracted increasing attention by provinces and regions in China with abundant tourism *** to low data availability,the current tourism literature lacks empirical evidence of the tourism network in lessdeveloped mountainous regions where the development of transport infrastructure is more *** paper aims to provide such evidence using Guangxi Zhuang Autonomous Region in China as a case *** User Generated Content(UGC)data,this study constructs a tourism network in *** integrating social network analysis with spatial interaction modelling,we compared the impact of two different transport infrastructures,highway and high-speed railway,on tourist flows,particularly in less-developed mountainous *** was found that the product of node centrality and flow could best describe the significant pushing and pulling forces on the flow of *** tourism by high-speed railway was sensitive to the position of trip destination on the whole tourism network but self-drive tourism was more sensitive to travelling *** increase of high-speed railway density is crucial to promote local tourism-led economic development,however,large-scale karst landforms in the study area present a significant obstacle to the construction of high-speed railways.

关键词： Tourism network Mountainous region User Generated Content Social network analysis Spatial interaction modelling Guangxi

来源：评论

学校读者我要写书评

暂无评论

A multiobjective flexible job shop scheduling method based on deep reinforcement learning 9

A multiobjective flexible job shop scheduling method based o...

引用

9th International Symposium on Sensors, Mechatronics, and Automation system, ISSMAS 2023

作者： Liu, Weiqi Chen, Hao Zhang, Jianming Wang, Yaozong College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou China Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Science Fujian Quanzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Fujian Quanzhou China

ISBN: (纸本)9781510672802

To address the multiobjective flexible job shop scheduling problem, this paper establishes a Markov Decision Process for Multiobjective Flexible Job-Shop Scheduling Problem, aiming to minimize makespan and total machine load. Additionally, a multiobjective optimization algorithm base deep reinforcement learning is proposed. Firstly, a multiobjective decomposition strategy is introduced to decompose the problem into a set of subproblems, and graph neural networks with identical structures are employed to represent the priority dispatching rules for each subproblem. Experimental results demonstrate that this approach exhibits better generalization, higher solution quality, and faster convergence compared to previous methods. © 2024 SPIE.

关键词： deep reinforcement learning flexible job shop scheduling problem multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

A Blackbox Fuzzing Based on Automated State Machine Extraction

A Blackbox Fuzzing Based on Automated State Machine Extracti...

引用

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Zhaowei Zhang Wenjing Yu Zibin Wang Youlin Xiang National Key Laboratory of Science and Technology on Information System Security Beijing China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

Currently, protocol fuzzing techniques mainly employ two approaches: greybox fuzzing based on mutation and blackbox fuzzing based on generation. Greybox fuzzing techniques use message exchanges between the protocol server and actual clients as seeds, and generate test cases through mutation. Although this approach can provide coverage information of the SUT's code and state space through instrumentation and feedback, its drawback lies in the relatively random mutation strategy, which makes it challenging to validate the SUT's message verification process. This paper addresses this limitation by utilizing artificial intelligence techniques to extract protocol state machines. It aims to overcome the reliance on manual work in blackbox fuzzing based on generation and leverage its advantages to generate more effective fuzzing test cases. The study utilizes Prompt-Learning technology to analyze the semantic information in protocol RFC documents, obtain corresponding intermediate representations, and extract protocol state machines from these representations. Taking the BGP protocol as an experimental subject, the experimental results demonstrate a certain level of accuracy in the obtained protocol state machines and the ability to generate test cases from these state machines, thereby enhancing the automation level of protocol fuzzing.

关键词：

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 38

DarkSAM: Fooling Segment Anything Model to Segment Nothing

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong 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 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

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. © 2024 Neural information processing systems foundation. All rights reserved.

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：