检索结果-内蒙古大学图书馆

5th International Conference on Computer Information Science and Artificial Intelligence, CISAI 2022

作者： Chen, Shengquan Jiang, Nan Wu, Zheng Wang, Zichen Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Beijing100124 China

ISBN: (纸本)9781510662520

Software vulnerabilities will make the system vulnerable to attack, affect the reliability of the software and cause information leakage, which will have a huge impact on enterprises or individuals. Vulnerabilities are inevitable in software development engineering. Therefore, relying on some methods or tools for continuous vulnerability analysis of code is the solution to minimize software vulnerabilities. We propose a neural network model - JSVulExplorer for static vulnerability analysis of the dynamic programming language JavaScript. The JSVulExplorer focuses on feature enhancement of data. We use pre-training to learn the semantic similarity between code slices, utilize abstract syntax trees to generate path information, and design positional encoding to use the path information. Based on transfer learning, we combine the pre-trained model with path information to improve vulnerability detection performance. Experiments show that JSVulExplorer has significantly improved precision and recall compared to previous models. It is verified that the dynamic event-based programming language can also use the static analysis method for vulnerability detection. © 2023 SPIE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation 41

SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Danni Ji, Jiayi Ma, Yiwei Guo, Tianyu Wang, Haowei Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University 361005 China Youtu Lab Tencent Shanghai China

In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in applying semi-supervised techniques to RES is the prevalence of noisy pseudo-labels, particularly at the boundaries of objects. SemiRES incorporates the Segment Anything Model (SAM), renowned for its precise boundary demarcation, to improve the accuracy of these pseudo-labels. Within SemiRES, we offer two alternative matching strategies: IoU-based Optimal Matching (IOM) and Composite Parts Integration (CPI). These strategies are designed to extract the most accurate masks from SAM's output, thus guiding the training of the student model with enhanced precision. In instances where a precise mask cannot be matched from the available candidates, we develop the Pixel-Wise Adjustment (PWA) strategy, guiding the student model's training directly by the pseudo-labels. Extensive experiments on three RES benchmarks-RefCOCO, RefCOCO+, and G-Ref reveal its superior performance compared to fully supervised methods. Remarkably, with only 1% labeled data, our SemiRES outperforms the supervised baseline by a large margin, e.g. +18.64% gains on RefCOCO val set. The project code is available at https://***/nini0919/SemiRES. Copyright 2024 by the author(s)

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction by Disentangled Subgraph Structure

引用

Tsinghua Science and Technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

Analysis and Research on Dynamic Measurements Technology 11th

Analysis and Research on Dynamic Measurements Technology

引用

11th International Conference on Communications, Signal Processing, and Systems, CSPS 2022

作者： Fu, Yingfang Huang, Haoxiang Zhang, Jianbiao Trusted Native Technology Department of Ant Group Beijing Beijing China Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Trusted Computing Beijing China

ISBN: (纸本)9789819923618

In cloud computing environments characterized by "dynamics", the traditional static measurement to ensure the trust of the platform system is difficult to guarantee the trust of four dimensions in the cloud computing environment, such as the platform system, computation, transmission, and storage. Dynamic measurement, as an important key technology to secure reliable system operation, has received much attention from academia and industry. This paper introduces the principles and characteristics of dynamic measurement and the common attack risks in the running system. Meanwhile, this paper surveys the state of the art of dynamic measurement schemes. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： trusted computing

来源：评论

学校读者我要写书评

暂无评论

PowerDetector:Malicious PowerShell Script Family Classification Based on Multi-Modal Semantic Fusion and Deep Learning

引用

China Communications 2023年第11期20卷 202-224页

作者： Xiuzhang Yang Guojun Peng Dongni Zhang Yuhang Gao Chenguang Li School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationWuhan 430072China School of Information Guizhou University of Finance and EconomicsGuiyang 550025China

Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland ***,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior ***,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and *** this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep ***,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge ***,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different ***,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family *** experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 ***,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.

关键词： deep learning malicious family detection multi-modal semantic fusion PowerShell

来源：评论

学校读者我要写书评

暂无评论

MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization 30

MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Tao Lin, Ze Li, Hui Ji, Jiayi Zhou, Yiyi Li, Guanbin Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computer Science and Engineering Sun Yat-sen University China

ISBN: (纸本)9782493814104

Given the long textual product information and the product image, Multi-modal Product Summarization (MPS) aims to increase customers' desire to purchase by highlighting product characteristics with a short textual summary. Existing MPS methods can produce promising results. Nevertheless, they still 1) lack end-to-end product summarization, 2) lack multi-grained multi-modal modeling, and 3) lack multi-modal attribute modeling. To improve MPS, we propose an end-to-end multi-grained multi-modal attribute-aware product summarization method (MMAPS) for generating high-quality product summaries in e-commerce. MMAPS jointly models product attributes and generates product summaries. We design several multi-grained multi-modal tasks to better guide the multi-modal learning of MMAPS. Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries. Extensive experiments on a real large-scale Chinese e-commence dataset demonstrate that our model outperforms state-of-the-art product summarization methods w.r.t. several summarization metrics. Our code is publicly available at: https://***/KDEGroup/MMAPS. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Attention Mixup: An Accurate Mixup Scheme Based On Interpretable Attention Mechanism for Multi-Label Audio Classification 48

Attention Mixup: An Accurate Mixup Scheme Based On Interpret...

引用

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

作者： Liu, Wuyang Ren, Yanzhen Wang, Jingru Ministry of Education Key Laboratory of Aerospace Information Security and Trusted Computing China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9781728163277

Mixup proves to be an efficient data augmentation method on audio classification tasks. Original mixup scheme directly mixes the waveform of two random samples, which not only ignores the temporal distribution of the sound events but may also interfere with the original sound events in another sample. This paper proposes Attention MixUp (AMU), which only selects those segments that contain sound events for mixup, rather than simply mixing the entire sample. AMU utilizes the attention maps of pretrained audio classification Vision Transformer (ViT) to filter out the patches on the spectrogram that are useful for classification and then selects the regions for mixup according to three different strategies. Experimental results show a remarkable improvement (+1.9 mAP) on state-of-the-art Audioset classification methods with either CNN or ViT backbone. Further experiments show that AMU achieves the performance gain by improving the accuracy on short events (0.1s to 2s) by an average of 6.8% while keeping the accuracy on longer events. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adapting Hierarchical Transformer for Scene-Level Sketch-Based Image Retrieval 5

Adapting Hierarchical Transformer for Scene-Level Sketch-Bas...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Yang, Jie Ke, Aihua Cai, Bo Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (纸本)9798400702051

Sketch-based image retrieval (SBIR) is an essential application of sketches. Research on object-level SBIR is relatively mature, but the study of more complex scene-level SBIR is still in its early stages. In order to advance this research, we investigate previous works and identify two main shortcomings: (1) insufficient utilization of multi-scale features from sketches and images, and (2) lack of effective modules to eliminate the substantial domain gap between them. To address these issues, we propose SketchRetriever, a hierarchical Transformer-based scene-level SBIR model. In our model, the hierarchical Transformer and compressors are capable of efficiently capturing feature maps at various granularities and compressing them into corresponding feature vectors, and the modality-specific Adapters can project the feature embeddings of sketches and images into the same feature space, thereby closing the domain gap between them. We adopt the adapter-tuning strategy, which not only considerably reduces the number of tunable parameters but also effectively avoids overfitting. Extensive experiments demonstrate that SketchRetriever significantly outperforms state-of-the-art methods on two benchmark datasets with lower fine-tuning overhead. © 2023 Copyright held by the owner/author(s).

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

How to Construct Public Timeline for RSA-Formed Time-Lock Cryptography 20th

How to Construct Public Timeline for RSA-Formed Time-Lock ...

引用

20th International Conference on Information Security and Cryptology, Inscrypt 2024

作者： Jin, Huixuan Peng, Cong Fu, Jintao Luo, Min Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China Henan Key Laboratory of Network Cryptography Technology Henan Zhengzhou China Inspur Academy of Science and Technology Jinan China

ISBN: (纸本)9789819647330

Time-Locked Puzzle (TLP) and timed-release encryption (T-RE) are both time-based locking mechanisms. The former requires the decryptor to perform a predetermined amount of computation, while the latter requires a trusted server to release the decryption information after a preset time, thereby sending information to the future. As research has progressed, many feature-rich TLPs and TREs have emerged. However, TLP and TRE still face issues in practical deployment. The imbalance in computation load with TLP can result in significant computational burdens in many deployment scenarios, while the timed release in TRE necessitates that the server remains online. To address these issues, our goal is to develop a multifunctional solution to offload the computational burden and allow the server to be offline. Our scheme focuses on RSA-based TLPs and builds upon the sequential TRE schemes proposed by Chvojka and Jager et al.(ESORICS’21). We construct a multi-timeline scheme that aggregates multiple functions and allows the server to be offline. The multi-timeline structure proposed in our scheme, consisting of a main timeline, sub-timelines, and reward timelines, allows different timelines to assume different functions, and the main timeline controls the information release of the remaining timelines to achieve an efficient puzzle-solving release mechanism. The reward timeline provides a transfer account for storing bonuses for entities that solve puzzles, which achieves a self-balancing mechanism for computing resources. Due to the completion of a transaction guaranteed by the adaptor signature and smart contract, which ensure the atomicity of the transaction, the scheme achieves a traceable fair trading mechanism and a public verification mechanism. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Accelerated Diffusion via High-Low Frequency Decomposition for Pan-Sharpening 39

Accelerated Diffusion via High-Low Frequency Decomposition f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Meng, Ge Huang, Jingjia Tu, Jingyan Wang, Yingying Lin, Yunlong Tu, Xiaotong Huang, Yue Ding, Xinghao Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China Institute of Artificial Intelligence Xiamen University China

ISBN: (纸本)157735897X

Pan-sharpening aims to preserve the spectral information of the multi-spectral (MS) image while leveraging the high-frequency details from the guided high-resolution panchromatic (PAN) image to enhance its spatial resolution. The key challenge is how to preserve the spectral information from the MS image and the spatial details from the PAN image as much as possible. Diffusion models have achieved favorable results in image restoration and synthesis tasks but suffer from excessive computational resource and time consumption. In this paper, we design a novel and computationally efficient diffusion-based pan-sharpening network that achieves accelerated diffusion while reducing task complexity by decoupling the high and low-frequency components of the fused image. Specifically, leveraging the information-preserving characteristic of the wavelet transformation, we introduce a Wavelet-based Low-frequency Diffusion Model (WLDM). WLDM generates the low-frequency coefficient of high-resolution MS (HRMS) image from the low-resolution MS (LRMS) image. This approach significantly reduces computational resources and complexity compared to the direct restoration of the HRMS image. Furthermore, we have devised a High-frequency Information Restoration Module (HIRM) to restore the high-frequency information in the HRMS image through the interaction of high-frequency coefficients from the PAN image in three directions. Extensive experiments on three different datasets demonstrate that our method outperforms existing approaches in both quantitative metrics, qualitative metrics, and inference efficiency. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Wavelet decomposition

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：