检索结果-内蒙古大学图书馆

Gupacker: Generalized Unpacking Framework for Android Malware

IEEE Transactions on Information Forensics and Security 2025年 20卷 4338-4352页

作者： Zheng, Tao Hou, Qiyu Chen, Xingshu Ren, Hao Li, Meng Li, Hongwei Shen, Changxiang Sichuan University School of Cyber Science and Engineering Chengdu610065 China Cyber Science Research Institute Sichuan University China Ministry of Education Key Laboratory of Data Protection and Intelligent Management Sichuan University Chengdu610065 China Ministry of Education Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China Hefei University of Technology School of Computer Science and Information Engineering China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology China University of Padua Department of Mathematics HIT Center Italy University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China

Android malware authors often use packers to evade analysis. Although many unpacking tools have been proposed, they face two significant challenges: 1) They are easily impeded by anti-analysis techniques employed by packers, preventing efficient collection of hidden Dex data. 2) They are typically designed to unpack a specific packer and cannot handle malware packed with mixed packers. Consequently, many packed malware samples evade detection. To bridge this gap, we propose Gupacker, a novel generalized unpacking framework. Gupacker offers a generic solution for first-generation holistic packer by customizing the Android system source code. It identifies the type of packer and selects an appropriate unpacking function, constructs a deeper active call chain to achieve generic unpacking of second-generation function extraction packers, and uses JNI function and instruction monitoring to handle third-generation virtual obfuscation packer. On this basis, we counteract a diverse array of anti-analysis techniques. We conduct extensive experiments on 5K packed Android malware samples, comparing Gupacker with 2 commercial and 4 state-of-the-art academic unpacking tools. The results demonstrate that Gupacker significantly improves the efficiency of Android malware unpacking with acceptable system overhead. We analyze real packed applications based on Gupacker and found several are second-packed by attackers, including WPS for Android, with tens of millions of users. We receive and responsibly report 13 0day vulnerabilities and also assist in the remediation of all vulnerabilities. © 2005-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

MS-SAM: Multi-scale SAM Based on Dynamic Weighted Agent Attention 31st

MS-SAM: Multi-scale SAM Based on Dynamic Weighted Agent Att...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yang, Enhui Zhang, Zhibin Engineering Research Center of Ecological Big Data Ministry of Education Key Laboratory of Wireless Networks and Mobile Computing Inner Mongolia University Hohhot010021 China

ISBN: (纸本)9789819620630

The Segment Anything Model (SAM), introduced in 2023, has made significant advancements in the field of computer vision. However, SAM faces two major challenges: limitations related to single-scale processing and high computational demands for large-scale data handling, which restrict its widespread adoption in practical applications. Therefore, we propose MS-SAM to achieve better segmentation performance at a lower cost. We introduce a multi-scale image encoder to handle images of varying scales and complexities. Additionally, we propose a dynamic weighted agent attention, which can flexibly and efficiently adjust attention distribution while reducing computational costs. We train MS-SAM on a 1/20 subset of the SA-1B dataset for instance segmentation using points or boxes as prompts. The results show that we maintain the accuracy with the SAM method while reducing the parameters by about 6 times. We give sufficient experimental results to demonstrate its effectiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SlagNet: A Real-Time Slag Segmentation Model Based on Context and Edge Fusion 16th

SlagNet: A Real-Time Slag Segmentation Model Based on Conte...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Liu, Kecheng Li, Jiangyun Yuan, Li School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing100083 China

ISBN: (纸本)9789819617760

In the process of iron and steel smelting, steel slag is inevitably produced as a byproduct. Accurately identifying steel slag is a prerequisite for controlling the content of steel slag. Conventional vision-based steel slag processing solutions are constrained by real-time performance or robustness against disturbances, rendering them directly applied in industrial sites. To address these issues, SlagNet, a steel slag segmentation network with real-time performance and strong disturbance resistance, is designed in this paper. By designing a lightweight branch to extract rich context information, and combining edge branches to supplement the slag edge information, 77.69 mIOU and 13.25 FPS are achieved in the field collection of slagging data set. The results indicate that SlagNet achieves the optimal balance between real-time performance and accuracy in comparison with other segmentation methods, thereby meeting the requirements of industrial sites. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Slags

来源：评论

学校读者我要写书评

暂无评论

Prediction of Rolling Force in Hot Rolling Process Based on Rollformer Model 16th

Prediction of Rolling Force in Hot Rolling Process Based on ...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Li, Qing Jiang, Pengyuan Yuan, Li School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing100083 China

ISBN: (纸本)9789819617760

In the steel manufacturing industry, the precise forecasting of rolling forces in the hot rolling process is vital for enhancing production efficiency and ensuring product quality. Traditional forecasting methods exhibit limitations when addressing the nonlinearity and variability of industrial data, and current deep learning models are slow to respond to real-time data, with room for improvement in predictive accuracy within dynamic production settings. This paper introduces the Rollformer deep learning model, which adeptly captures intricate nonlinear patterns through the self-attention mechanism's nonlinear transformation capabilities, and boosts sensitivity and adaptability to data variability via adaptive weight distribution. The Rollformer model also pioneers the Roll Self-attention mechanism, leveraging probabilistic sparsity to diminish computational complexity and accelerate the model’s response. Additionally, it employs a generative decoder for swift long-sequence predictions, thereby augmenting the model’s predictive precision. Validated with extensive real-world data from steel mills, the Rollformer model demonstrates superior predictive accuracy and response speed when compared to other Transformer-based deep learning models such as Autoformer and Conformer. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Rethinking-based Code Summarization with Chain of Comments 31

Rethinking-based Code Summarization with Chain of Comments

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Liuwen He, Hongkui Huang, Hailin Wang, Jiexin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9798891761964

Automatic code summarization aims to generate concise natural language descriptions (summary) for source code, which can free software developers from the heavy burden of manual commenting and software maintenance. Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the significant heterogeneity gap between code and summary. Moreover, existing methods lack a human-like re-check process to evaluate whether the generated summaries match well with the code. To address these two limitations, we introduce RBCoSum, a novel framework that incorporates the generated Chain Of Comments (COC) as auxiliary intermediate information for the model to bridge the gap between code and summaries. Also, we propose a rethinking process where a learned ranker trained on our constructed ranking dataset scores the extent of matching between the generated summary and the code, selecting the highest-scoring summary to achieve a re-check process. We conduct extensive experiments to evaluate our approach and compare it with other automatic code summarization models as well as multiple code Large Language Models (LLMs). The experimental results show that RBCoSum is effective and outperforms baselines by a large margin. The human evaluation also proves the summaries generated with RBCoSum are more natural, informative, useful, and truthful. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Secure Beamforming for IRS-Assisted IoT Communication Using a Generative Diffusion Model-enabled Optimization Approach

引用

IEEE Internet of Things Journal 2025年第10期12卷 13398-13414页

作者： Zhang, Jing Liu, Zheng Feng, Xin Yang, Hongwei Liang, Shuang Changchun University of Science and Technology College of Computer Science and Technology Changchun130022 China Northeast Normal University School of Information Science and Technology Changchun130117 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China

The spatial correlation between the main and eavesdropping channels impacts the effectiveness of beamforming technology in securing the IoT communication system. This study proposes an IRS-assisted secure beamforming scheme (IRSSBS) for a multi-user IoT system under imperfect channel state information (CSI). The security issue, constrained by channel spatial correlation, is formulated as a non-convex optimization problem with probabilistic constraints. To address this, we introduce a novel Actor-Critic algorithm combined with a Generative Diffusion Model (AC-GDM). This approach jointly optimizes the base station (BS) precoding matrix and the intelligent reflecting surface (IRS) phase shift matrix, subject to constraints on transmit power and phase shifts. The AC-GDM algorithm utilizes a denoising process to recover the optimal beamforming solution from the Gaussian noise inherent in the multi-user wireless channel environment. Simulation results demonstrate that the minimum achievable secrecy rate of the IRS-SBS outperforms the artificial noise (AN) scheme and the beamforming (BF) scheme by approximately 1.9576 and 2.3596 bps/Hz, respectively. These results validate the effectiveness of IRS-SBS in significantly mitigating the impact of channel spatial correlation on the security of IoT communication systems. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Lightweight Dual Grouped Large-Kernel Convolutions for Salient Object Detection Network 31st

Lightweight Dual Grouped Large-Kernel Convolutions for Sali...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Liu, Jiajie Zhang, Zhibin Engineering Research Center of Ecological Big Data Ministry of Education Beijing China Key Laboratory of Wireless Networks and Mobile Computing Inner Mongolia University Hohhot010021 China

ISBN: (纸本)9789819620609

Most existing Salient Object Detection (SOD) methods focus on achieving better performance, often resulting in models with a large number of parameters. However, there is limited research on lightweight models in this field. To address this gap, our goal is to maintain performance while reducing the number of network parameters. Thanks to the development of large-kernel convolutions in recent years, we have improved the U2Net as the base network by adding our lightweight dual large-kernel fusion module. Our module better utilizes the depth information of U2Net and, due to the large receptive field of large-kernel convolutions, better captures the relationships between image elements. This allows our network to remain lightweight while maintaining performance. We designed a large-kernel (DLK) fusion module and a lightweight dual grouped large-kernel Unet network (DGLKUNET). Our network uses SRUS (an improved Residual U-blocks module, RUS) to construct DGLKUNET that predicts image contours and labels. Compared to the base RUS network (U2Net), our network reduces the number of parameters by up to 70% and the computational cost by 40% while maintaining performance. Evaluation results on five datasets demonstrate the performance of our lightweight network. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Secure Multi-way Join Query and Its Bench-Marking with Trusted Execution Environments 2nd

Secure Multi-way Join Query and Its Bench-Marking with Tru...

引用

2nd International Conference on data Security and Privacy Protection, DSPP 2024

作者： Zhao, Yi Zhao, Sen Lv, Siyi School of Cyber Engineering Xidian University Xi’an China State Key Laboratory of Integrated Service Networks Xidian University Xi’an China Key Laboratory of Data and Intelligent System Security Ministry of Education Nankai University Tianjin China

ISBN: (纸本)9789819785452

Because of server-untrustable model in outsourcing encrypted database system, it’s fatal for data owners to keep their data confidential under complex query operations performed by database servers. Trusted Execution Environments (TEEs) provide a secure space for privacy computation via hardware-based methods to increase the efficiency of database system, and it ensures the availability of computing directly on sensitive data in untrusted outsourcing database servers. However, while various query schemes are designed under the combination of encrypted database and TEEs, designing an available and secure scheme for join queries on multiple data tables with TEEs remains an open problem. Besides, previous works also devote less to bench-marking multi-way joins on TEEs. In our work, we extend binary join query scheme into multi-way forms in encrypted database system based on TEEs. It combines various join algorithms based on hash functions (hash-based, radix-based, etc.) with parallelized optimizing mechanism. Besides, we do bench-marking with TEEBench framework on those multi-way join schemes in three-way forms using both cache-fit and cache-exceed datasets and do different evaluation on two TEEs hardware platforms (Intel SGX and AMD SEV) to show its availability. After that, we also propose a multi-way join scheme with access pattern protection through the combination between our previous scheme and oblivious I/O methods. With the evaluation of its efficiency and memory leakage, we can also verify the feasibility of our access-pattern-protected multi-way join scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

Transformer-based multi-level attention integration network for video saliency prediction

引用

Multimedia Tools and Applications 2025年第13期84卷 11833-11854页

作者： Tan, Rui Sun, Minghui Liang, Yanhua Software College Jilin University Qianjin Street Jilin Changchun130012 China College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China

Most existing models for video saliency prediction heavily rely on 3D convolutional operations to extract spatio-temporal features. However, it is worth noting that 3D convolution produces a local receptive field, which may struggle to capture long-range spatio-temporal dependencies effectively. To compensate for such shortage, this paper introduces a novel approach called the Transformer-based Multi-level Attention Integration Network (TMAI-Net) for video saliency prediction. TMAI-Net is designed as a two-stream encoder-decoder model, carefully integrating multi-level features of semantic information. Our model incorporates a Multi-level Interactive Attention(MLIA) module and a Transformer, both implemented based on self-attention mechanism, which are placed at different levels of the model to capture long-range spatio-temporal feature dependencies. Additionally, our model operates on input video frames and attentional patches, allowing the Transformer module to capture structural similarities between related objects in global features and attention features. This, in turn, enables the model to allocate increased attention to salient areas. The efficacy of our proposed approach is validated through extensive experiments conducted on three widely recognized benchmark datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Towards a Theoretical Understanding of Semi-Supervised Learning Under Class Distribution Mismatch

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4853-4868页

作者： Pan Du Suyun Zhao Puhui Tan Zisen Sheng Zeyu Gan Hong Chen Cuiping Li School of Information Renmin University of China Beijing China Engineering Research Center of Database and Business Intelligence Ministry of Education (MOE) Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education (MOE) Beijing China School of Statistics Renmin University of China Beijing China

Semi-supervised learning (SSL) confronts a formidable challenge under class distribution mismatch, wherein unlabeled data contain numerous categories absent in the labeled dataset. Traditional SSL methods undergo performance deterioration in such mismatch scenarios due to the invasion of those instances from unknown categories. Despite some technical efforts to enhance SSL by mitigating the invasion, the profound theoretical analysis of SSL under class distribution mismatch is still under study. Accordingly, in this work, we propose Bi- Objective Optimization Mechanism (BOOM) to theoretically analyze the excess risk between the empirical optimal solution and the population-level optimal solution. Specifically, BOOM reveals that the SSL error is the essential contributor behind excess risk, resulting from both the pseudo-labeling error and invasion error. Meanwhile, BOOM unveils that the optimization objectives of SSL under mismatch are binary: high-quality pseudo-labels and adaptive weights on the unlabeled instances, which contribute to alleviating the pseudo-labeling error and the invasion error, respectively. Moreover, BOOM explicitly discovers the fundamental factors crucial for optimizing the bi-objectives, guided by which an approach is then proposed as a strong baseline for SSL under mismatch. Extensive experiments on benchmark and real datasets confirm the effectiveness of our proposed algorithm.

关键词： Training Labeling Semisupervised learning Predictive models Optimization Perturbation methods Entropy data models Annotations Upper bound

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：