检索结果-内蒙古大学图书馆

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Pan, Zhiyuan Hu, Xing Xia, Xin Zhan, Xian Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Huawei Software Engineering Application Technology Lab Hangzhou China The Hong Kong Polytechnic University Hong Kong School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400702174

The number of vulnerabilities reported in open source software has increased substantially in recent years. security patches provide the necessary measures to protect software from attacks and vulnerabilities. In practice, it is difficult to identify whether patches have been integrated into software, especially if we only have binary files. Therefore, the ability to test whether a patch is applied to the target binary, a.k.a. patch presence test, is crucial for practitioners. However, it is challenging to obtain accurate semantic information from patches, which could lead to incorrect results. In this paper, we propose a new patch presence test framework named Ppt4j (Patch Presence Test forJava Binaries). Ppt4j is designed for open-source Java libraries. It takes Java binaries (i.e. bytecode files) as input, extracts semantic information from patches, and uses feature-based techniques to identify patch lines in the binaries. To evaluate the effectiveness of our proposed approach Ppt4j, we construct a dataset with binaries that include 110 vulnerabilities. The results show that Ppt4j achieves an F1 score of 98.5% with reasonable efficiency, improving the baseline by 14.2%. Furthermore, we conduct an in-the-wild evaluation of Ppt4j on JetBrains IntelliJ IDEA. The results suggest that a third-party library included in the software is not patched for two CVEs, and we have reported this potential security problem to the vendor. © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

CoKV: Optimizing KV Cache Allocation via Cooperative Game

arXiv

引用

arXiv 2025年

作者： Sun, Qiheng Zhang, Hongwei Xia, Haocheng Zhang, Jiayao Liu, Jinfei Ren, Kui The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data China Security China Siebel School of Computing and Data Science University of Illinois Urbana-Champaign United States

Large language models (LLMs) have achieved remarkable success on various aspects of human life. However, one of the major challenges in deploying these models is the substantial memory consumption required to store key-value pairs (KV), which imposes significant resource demands. Recent research has focused on KV cache budget allocation, with several approaches proposing head-level budget distribution by evaluating the importance of individual attention heads. These methods, however, assess the importance of heads independently, overlooking their cooperative contributions within the model, which may result in a deviation from their true impact on model performance. In light of this limitation, we propose CoKV, a novel method that models the cooperation between heads in model inference as a cooperative game. By evaluating the contribution of each head within the cooperative game, CoKV can allocate the cache budget more effectively. Extensive experiments show that CoKV achieves state-of-the-art performance on the LongBench benchmark using LLama-3-8B-Instruct and Mistral-7B models. Code is provided in https://***/nawei1010/CoKV. Copyright © 2025, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

BPVFL: A Bidirectional Privacy-Preserving Verifiable Federated Learning Framework with Homomorphic Encryption

BPVFL: A Bidirectional Privacy-Preserving Verifiable Federat...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Jingwei Chen, Sijing Zhu, Junrong Sun, Rong Du, Xiaojiang Guizani, Mohsen Xidian University Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Xidian University State Key Laboratory of Isn Xi'an710071 China Stevens Institute of Technology Department of Electrical and Computer Engineering Hoboken United States Department of Machine Learning Abu Dhabi999041 United Arab Emirates

ISBN: (纸本)9798350351255

Federated learning, while advancing data privacy, faces risks of sensitive information leakage through parameter updates, making it susceptible to inference and data reconstruction attacks. Fraudulent behaviors by central servers or clients can undermine the integrity of model training, thereby reducing accuracy and affecting decision-making quality. This paper introduces a bidirectional, privacy-preserving verifiable federated learning framework(BPVFL) built on homomorphic encryption and a novel three-party zero-knowledge protocol. This framework guarantees the integrity of server aggregation and the credibility of the information uploaded by clients. Experimental results demonstrate that BPVFL effectively protects client privacy, prevents fraud by servers and certain clients, and efficiently handles numerous client disconnections with minimal overhead. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of handlebar defect detection method based on machine recognition

Design and implementation of handlebar defect detection meth...

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2024

作者： Zhang, Tong Ren, Sunan Zhang, Wenjing Liu, Yajun School of Computer Science and Engineering Xi’an University of Technology Shaanxi Xi’an 710048 China Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi’an University of Technology Shaanxi Xi’an 710048 China

ISBN: (纸本)9781510689275

As an important part of electric vehicles, handlebar installation defects are an important factor in the failure of electric vehicles. In the production process, many large-scale manufacturers still assemble the handlebar manually by workers, and the workload is large, and there may always be errors such as tilting, concave and other assembly defects, and due to the large number of assemblies, the identification of the handlebar assembly defects through manual work will have a significant impact on work efficiency. Therefore, the use of machine recognition instead of traditional manual recognition has become the trend of the development of the industry. In this study, we designed a defect detection method based on machine recognition. First, we collect the image data of the electric vehicle and extract the region of interest group of the electric vehicle through image preprocessing. Then, according to the area of interest information, the electric vehicle baseline group is determined, and the electric vehicle baseline group is used to determine the basis for the handlebar assembly defects. Finally, the angle and distance information between the reference lines are calculated to determine the defects of the handlebar installation. Experiments show that our method can not only reduce the consumption of human resources in the defect detection of electric vehicle handlebar installation by electric vehicle manufacturers, but also use strict filtering conditions to obtain reliable reference lines and detection points in the region of interest, so that the subsequent detection results are more reliable and credible, and the detection error is reduced. © 2025 SPIE.

关键词： datum line defect detection Handlebar Installation Defects machine recognition

来源：评论

学校读者我要写书评

暂无评论

Defense Against Adversarial Attacks via Adversarial Noise Denoising Networks in Image Recognition

Defense Against Adversarial Attacks via Adversarial Noise De...

引用

2023 International Conference on Networking and Network Applications, NaNA 2023

作者： Li, Chengxuan Yang, Zhou Xiao, Yang Liu, Haozhao Zhang, Yuning Pei, Qingqi Xidian University State Key Laboratory of Integrated Services Networks Xi'an China School of Telecommunications Engineering Xidian University Xi'an China School of Cyber Engineering Xidian University Xi'an China Xidian University Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an China

ISBN: (纸本)9798350327380

Deep learning-based image recognition technology has significantly advanced the development of modern industrial intelligence. However, the issue of image adversarial examples that follows has gradually garnered the attention of researchers. By injecting adversarial disturbances that are difficult for humans to detect into the image, the deep learning model generates incorrect results, severely impacting the security of deep learning applications. To address this problem and improve the accuracy and robustness of deep learning image recognition models, a combined adversarial examples detection method based on residual learning and difference assessment has been proposed. To start, an image denoising module, based on residual learning and named ANDNet, is designed. This method incorporates a depth separable convolution structure and conducts step processing on the channel number of the hidden layer in ANDNet, which significantly reduces the model's memory consumption and improves its computational efficiency. In addition, the difference assessment involves computing the l1 norm distance between the original image and the denoised image softmax output of the classification model, to measure the disparity between the input image before and after denoising. The obtained detection threshold from the training dataset is integrated with this difference evaluation to accomplish the task of testing the input image for adversarial detection. Both theoretical analysis and experimental results confirm the effectiveness of the ANDNet noise reduction network, as well as the efficacy of the adversarial examples detection scheme in identifying adversarial examples. The model exhibits exceptional performance in terms of detection accuracy and F1 value. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models

arXiv

引用

arXiv 2025年

作者： He, Yu Li, Boheng Liu, Liu Ba, Zhongjie Dong, Wei Li, Yiming Qin, Zhan Ren, Kui Chen, Chun The State Key Laboratory of Blockchain and Data Security Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model’s training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to complete output logits (i.e., logits-based attacks), which are usually not available in practice. In this paper, we study the vulnerability of pre-trained LLMs to MIAs in the label-only setting, where the adversary can only access generated tokens (text). We first reveal that existing label-only MIAs have minor effects in attacking pre-trained LLMs, although they are highly effective in inferring fine-tuning datasets used for personalized LLMs. We find that their failure stems from two main reasons, including better generalization and overly coarse perturbation. Specifically, due to the extensive pretraining corpora and exposing each sample only a few times, LLMs exhibit minimal robustness differences between members and non-members. This makes token-level perturbations too coarse to capture such differences. To alleviate these problems, we propose PETAL: a label-only membership inference attack based on PEr-Token semAntic simiLarity. Specifically, PETAL leverages token-level semantic similarity to approximate output probabilities and subsequently calculate the perplexity. It finally exposes membership based on the common assumption that members are ‘better’ memorized and have smaller perplexity. We conduct extensive experiments on the WikiMIA benchmark and the more challenging MIMIR benchmark. Empirically, our PETAL performs better than the extensions of existing label-only attacks against personalized LLMs and even on par with other advanced logit-based attacks across all metrics on five prevalent open-source LLMs1. Our study highlights that pre-trained LLMs remain vulnerable to privacy risks posed by MIAs even in the most challenging and realistic setting, calling for attention to develop more effective defenses. Copyright © 20

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Channel Capacity Analysis for Diffusive Molecular Communication with a Partly Covered Comprehensive Reactive Receiver

Channel Capacity Analysis for Diffusive Molecular Communicat...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Zhu, Junning Liao, Xuening Wu, Zhenqiang Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an China School of Computer Science Shaanxi Normal University Xi’an China Shaanxi Key Laboratory for Network Computing and Security Shaanxi Xi’an710048 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Molecular communication (MC) is a technology that utilizes microscopic particles such as molecules to communicate at the microscopic scale in living organisms. The nanomachine receiver as a critical part of MC has been extensively investigated. However, existing analyses of nanomachine receivers rarely consider the effects of various chemical reactions. In the few papers that considered the effect of chemical reaction on the channel, the effect of receptor coverage on the receiver surface was also not considered. To fill this gap, this paper studies the variation of channel capacity with coverage rate when the surface of the nanomachine receiver is partially covered with the receptors. This paper derived numerical results of channel capacity under the scenarios above and carried out the numerical simulations. The simulation results show that the channel capacity increases with the increase of coverage, which can guide the design of high-performance nanomachines. © 2022 IEEE.

关键词： Reaction rates

来源：评论

学校读者我要写书评

暂无评论

A Channel-Wise Guidance Sparse Transformer for Effective Dark Image Enhancement

A Channel-Wise Guidance Sparse Transformer for Effective Dar...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Haiyan Jin Yifan Shuai Fengyuan Zuo Haonan Su Zhaolin Xiao Bin Wang Yuanlin Zhang Xi’an University of Technology China Shaanxi Key Laboratory for Network Computing and Security Technology China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Dark Image Enhancement (DIE) aims to improve contrast and restore details for captured images under low illumination. Currently, traditional Transformer methods have achieved significant performance in the DIE problem; however, all-pairs correlation computation is redundant in learning key properties and restoring high-order representations. To alleviate this problem, we introduce a Channel-wise Guidance Sparse Transformer framework, namely CGSformer, which not only adaptively selects the key channel-wise representations through a threshold operator, but also keeps the most useful self-attention values for feature restoration guided by the selected information. Besides, we introduce a Bidirectional Gate Feed-Forward (BGFF) network to aggregate features to better facilitate high-quality image reconstruction. The experiments are conducted on representative datasets, showing that our CGSformer consistently achieves state-of-the-art performance on widely used benchmarks.

关键词： Correlation Aggregates Lighting Logic gates Benchmark testing Transformers Image restoration Image enhancement Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

HiCoCS: High Concurrency Cross-Sharding on Permissioned blockchains

引用

IEEE Transactions on Computers 2025年第07期74卷 2168-2182页

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Lu, Di Zhang, Yushu Shen, Yulong Xidian University School of Computer Science and Technology China Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China Zhejiang Lab Zhejiang Hangzhou311121 China Shaanxi Key Laboratory of Network and System Security Xi’an710071 China Jiangxi University of Finance and Economics School of Computing Nanchang330013 China Jiangxi University of Finance and Economics Nanchang330013 China

As the foundation of the Web3 trust system, blockchain technology faces increasing demands for scalability. Sharding emerges as a promising solution, but it struggles to handle highly concurrent cross-shard transactions (CSTxs), primarily due to simultaneous ledger operations on the same account. Hyperledger Fabric, a permissioned blockchain, employs multi-version concurrency control for parallel processing. Existing solutions use channels and intermediaries to achieve cross-sharding in Hyperledger Fabric. However, the conflict problem caused by highly concurrent CSTxs has not been adequately resolved. To fill this gap, we propose HiCoCS, a high concurrency cross-shard scheme for permissioned blockchains. HiCoCS creates a unique virtual sub-broker for each CSTx by introducing a composite key structure, enabling conflict-free concurrent transaction processing while reducing resource overhead. The challenge lies in managing large numbers of composite keys and mitigating intermediary privacy risks. HiCoCS utilizes virtual sub-brokers to receive and process CSTxs concurrently while maintaining a transaction pool. Batch processing is employed to merge multiple CSTxs in the pool, improving efficiency. We explore composite key reuse to reduce the number of virtual sub-brokers and lower system overhead. Privacy preservation is enhanced using homomorphic encryption. Evaluations show that HiCoCS improves cross-shard transaction throughput by 3.5-20.2 times compared to the baselines. © 1968-2012 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

FSVM: Federated Support Vector Machines for Smart City 17th

FSVM: Federated Support Vector Machines for Smart City

引用

17th EAI International Conference on Tools for Design, Implementation and Verification of Emerging Information Technologies, TridentCom 2022

作者： Ma, Lichuan Tang, Lizhen Gao, Longxiang Pei, Qingqi Ding, Ming Shannxi Key Laboratory of Blockchain and Secure Computing Xidian University Xi’an China Qilu University Jinan China Information Privacy and Security Group Data61 Commonwealth Scientific and Industrial Research Organization Silicon Valley Australia

ISBN: (纸本)9783031334573

By putting digital technology and vast volume of data together, smart city becomes an emerging city paradigm for intelligent city management and operation. As one of the most popular artificial intelligent algorithms, support vector machines (SVMs) have been widely adopted for classification in various smart city applications. Due to the explosion of data and rigorous privacy requirements, an SVM classifier needs to be trained in a distributed and privacy-preserving manner. To achieve this, a federated SVM (FSVM) scheme is proposed to collaboratively and privately train an SVM classifier by combining the alternating direction method of multipliers (ADMM) with secret sharing. Specifically, the FSVM consists of FSVM-C and FSVM-S to deal with two cases of data partitioning by examples and features, respectively. By implementing the FSVM scheme on the real-word dataset MNIST, the efficiency and effectiveness of both FSVM-S and FSVM-C are verified by comprehensive experimental results. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Support vector machines

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：