检索结果-内蒙古大学图书馆

8th International Congress on Edge Computing, EDGE 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Tian, Yun Wu, Bin Shi, Jiaoli Zhang, Caicai Xu, Du School of Computer and Big Data Science Jiujiang University Jiujiang332005 China Jiujiang Key Laboratory of Network and Information Security Jiujiang332005 China School of Modern Information Technology Zhejiang Polytechnic University of Mechanical and Electrical Engineering Hangzhou310053 China

ISBN: (纸本)9783031770685

The development of cloud computing and the widespread application of cloud services have made outsourcing services more convenient. The need for individuals and businesses to store and manipulate the graph data they generate is growing rapidly. The unreliability and insecurity of cloud servers make outsourcing graph data a great risk of information leakage. To effectively protect data security, encrypting outsourced data is a useful method. The adjacent vertex query is a very commonly used and fundamental operation, and similarity search is a widely used and powerful tool to improve the scope and functionality of queries. After outsourcing encrypted sparse graph data to cloud servers, it becomes very inconvenient to use and manipulate the data. In this work, we present a scheme to realize the adjacent vertex query supporting similarity search on sparse graph data in cloud environment (SSAQ), which also protects the security of the information. This work uses edit distance and the searchable encryption principle to construct query index, and next implement the similar adjacent vertex query on cloud server. This work provides a formal security analysis, and also gives the experimental comparison and analysis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Understanding User Passwords through Parsing Tree

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wang, Ding Shan, Xuan Wu, Yuxuan Jia, Chunfu Nankai University College of Cryptology and Cyber Science Tianjin300350 China Ministry of Education of China Henan Key Laboratory of Network Cryptography Key Laboratory of Cyberspace Security China Nankai University Tianjin Key Laboratory of Network and Data Security Technology Tianjin300350 China

Passwords are today's dominant form of authentication, and password guessing is the most effective method for evaluating password strength. Most password guessing models (e.g., PCFG, Markov, and RFGuess) regard passwords as sequences composed of basic units (i.e., characters/segments), with the information flow being unidirectional (i.e., predicting the next unit based on the preceding units). However, modeling passwords in a single direction fails to capture users' password creation behavior that is actually impacted by the full password context. Through an in-depth analysis of real-world passwords, we reveal that users often create passwords around a central keyword, like common words, names, or dates, and then embellish them with numbers or symbols. Based on this observation, we, for the first time, attempt to parse passwords as trees. Unlike existing sequence models, trees can reveal the semantic connections within passwords and the logical thought processes users follow when creating passwords. For instance, in the password iloveyou, the basic units i and you are semantically dependent on the predicate love, forming a natural tree structure. We propose a trawling guessing model called PassTree and a targeted guessing model based on personally identifiable information (PII), named PassTree-PII. Our extensive experiments demonstrate the effectiveness of our models: (1) PassTree outperforms its leading counterparts by 0.38%-2.51% when guessing numbers are below 107 (2) PassTree-PII achieves a cracking rate comparable to the state-of-the-art RFGuess-PII proposed in USENIX Security'23, but operates significantly more efficiently, using only 0.87% of the memory and being 16.60 times faster. Our work provides a new perspective on understanding user passwords and demonstrates a feasible technical route of applying tree structures to password guessing. © 2025 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

CLIPURE: PURIFICATION IN LATENT SPACE VIA CLIP FOR ADVERSARIALLY ROBUST ZERO-SHOT CLASSIFICATION

arXiv

引用

arXiv 2025年

作者： Zhang, Mingkun Bi, Keping Chen, Wei Guo, Jiafeng Cheng, Xueqi State Key Lab of AI Safety CAS Key Lab of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts "a photo of a .". Purification is the path we choose since it does not require adversarial training on specific attack types and thus can cope with any foreseen attacks. We then formulate purification risk as the KL divergence between the joint distributions of the purification process of denoising the adversarial samples and the attack process of adding perturbations to benign samples, through bidirectional Stochastic Differential Equations (SDEs). The final derived results inspire us to explore purification in the multi-modal latent space of CLIP. We propose two variants for our CLIPure approach: CLIPure-Diff which models the likelihood of images’ latent vectors with the DiffusionPrior module in DaLLE-2 (modeling the generation process of CLIP’s latent vectors), and CLIPure-Cos which models the likelihood with the cosine similarity between the embeddings of an image and "a photo of a.". As far as we know, CLIPure is the first purification method in multi-modal latent space and CLIPure-Cos is the first purification method that is not based on generative models, which substantially improves defense efficiency. We conducted extensive experiments on CIFAR-10, ImageNet, and 13 datasets that previous CLIP-based defense methods used for evaluating zero-shot classification robustness. Results show that CLIPure boosts the SOTA robustness by a large margin, e.g., from 71.7% to 91.1% on CIFAR10, from 59.6% to 72.6% on ImageNet, and 108% relative improvements of average robustness on the 13 datasets over previous SOTA. The code is available at https://***/TMLResearchGroup-cas/CLIPure. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

DSDIR: A Two-Stage Method for Addressing Noisy Long-Tailed Problems in Malicious Traffic Detection

DSDIR: A Two-Stage Method for Addressing Noisy Long-Tailed P...

引用

International Conference on Acoustics, Speech, and Signal Processing (IcasSP)

作者： Guoliang Li Ruiqi Zhang Zhe Sun Lingkai Xing Yu Zhang College of Cyber Science Nankai University China Tianjin Key Laboratory of Network and Data Security Technology China Key Laboratory of Data and Intelligent System Security Ministry of Education China College of Computer Science Nankai University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, deep learning based malicious traffic detection (MTD) systems have demonstrated remarkable success. However, their effectiveness tend to decrease because most malicious traffic datasets are suffered from noisy-labeled and long-tailed problems. While numerous approaches have been developed to address these two problems individually, they become inefficient when confronting the combined challenge of noisy long-tailed data, as they typically tackle only a single adverse factor at a time. This paper proposes a two-stage method called Distribution-aware sample Selection and Dynamic Instance-based Relabeling (DSDIR), which simultaneously addresses the impacts of noisy-labeled and long-tailed problems. In the first stage, a noise-independent clean sample selection method is designed to obtain a clean dataset, which converts negative effects of the long-tailed problem into positive ones. In the second stage, dynamic instance-based relabeling is designed to train a model and improve the dataset’s quality simultaneously. Eventually, DSDIR not only produces a balanced and noise-tolerant model but also obtains a clean dataset. Experimental results demonstrate that in the high noise condition of 60% and 80%, the accuracy rate of DSDIR is 5% higher than the state-of-the-art methods. Our code is available at https://***/nku-ligl/DSDIR.

关键词： Deep learning Computer vision Heavily-tailed distribution Codes Accuracy Noise Speech recognition Acoustics Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

IEEE Symposium on High-Performance Computer Architecture

作者： Ziming Yuan Lei Dai Wen Li Jie Zhang Shengwen Liang Ying Wang Cheng Liu Huawei Li Xiaowei Li Jiafeng Guo Peng Wang Renhai Chen Gong Zhang State Key Lab of Processors Institute of Computing TechnologyCAS University of Chinese Academy of Sciences School of Computer and Information Technology Shanxi University School of Computer Science Peking University Zhongguancun National Laboratory Beijing Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Huawei Technologies Co. Ltd. China

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Training Quantization (signal) Philosophical considerations Graphics processing units Computer architecture Throughput Vectors User experience System-on-chip Indexes

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution

arXiv

引用

arXiv 2025年

作者： Zhu, Jizhao Shi, Akang Li, Zixuan Bai, Long Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science Shenyang Aerospace University Shenyang China

In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution. Existing robust benchmark datasets have two key limitations: 1) They generate only a limited range of perturbations for a single Information Extraction (IE) task, which fails to evaluate the robustness of UIE models effectively;2) They rely on small models or handcrafted rules to generate perturbations, often resulting in unnatural adversarial examples. Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench, which utilizes LLMs to generate more diverse and realistic perturbations across different IE tasks. Based on this dataset, we comprehensively evaluate existing UIE models and reveal that both LLM-based models and other models suffer from significant performance drops. To improve robustness and reduce training costs, we propose a data-augmentation solution that dynamically selects hard samples for iterative training based on the model’s inference loss. Experimental results show that training with only 15% of the data leads to an average 7.5% relative performance improvement across three IE tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

TransMatch: Employing Bridging Strategy to Overcome Large Deformation for Feature Matching in Gastroscopy Scenario

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zhu, Guosong Qin, Zhen Yu, Linfang Ding, Yi Qin, Zhiguang University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province Chengdu611731 China Industrial Research Institute Chengdu610000 China

Feature matching is widely applied in the image processing field. However, both traditional feature matching methods and previous deep learning-based methods struggle to accurately match the features with severe deformations and large displacements, particularly in gastroscopy scenario. To fill this gap, an effective feature matching framework named TransMatch is proposed, which addresses the largely displacements issue by matching features with global information leveraged via Transformer structure. To address the severe deformation of features, an effective bridging strategy with a novel bidirectional quadratic interpolation network is employed. This bridging strategy decomposes and simplifies the matching of features undergoing severe deformations. A deblurring module for gastroscopy scenario is specifically designed to address the potential blurriness. Experiments have illustrated that proposed method achieves state-of-the-art performance of feature matching and frame interpolation in gastroscopy scenario. Moreover, a large-scale gastroscopy dataset is also constructed for multiple tasks. © 1982-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid-Feature-Based Autoencoder Model for Predicting Traffic Flow to Accelerate Ambulance Medical Response Time in Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第9期12卷 11397-11407页

作者： Li, Yongmeng Tian, Yu Liu, Wenjian Gao, Longxiang Tian, Hui Xing, Lumin The First Affiliated Hospital of Shandong First Medical University Shandong Provincial Qianfoshan Hospital Shandong Key Laboratory of Digital Diagnosis and Treatment of Thoracic Oncology Shandong Engineering Research Center of Intelligent Surgery Shandong Jinan250014 China Qilu Hospital of Shandong University Department of Thoracic Surgery Shandong Jinan250012 China City University of Macau Faculty of Data Science China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250000 China The First Affiliated Hospital of Shandong First Medical University Shandong Provincial Qianfoshan Hospital Shandong Key Laboratory of Digital Diagnosis and Treatment of Thoracic Oncology Shandong Jinan250014 China

Traffic congestion during ambulance travel can delay medical response times. With the growing availability of traffic data, computational methods for traffic flow prediction are attracting significant attention. However, current computational prediction models have the following shortcomings. Fully connected networks require extensive feature engineering yet struggle to capture local traffic flow features. Their high parameter count increases training time and overfitting risk, while varying traffic conditions hinder model generalization. Therefore, in this work, we propose a hybrid-feature-based autoencoder (HFAE) model to predict traffic flow and accelerate ambulance medical response time in Internet of Vehicles. Specifically, the HFAE model simultaneously considers local features from the convolutional neural network and global features from the fully connected neural network. Additionally, the HFAE model uses an autoencoder to reconstruct the original input, capturing the intrinsic structure of the traffic flow data. Specifically, the root mean-squared error and mean absolute error scores of the HFAE model are better than those of the three mainstream models. © 2014 IEEE.

关键词： Ambulances

来源：评论

学校读者我要写书评

暂无评论

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction

arXiv

引用

arXiv 2025年

作者： Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Shaanxi Xi’an China

Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4% in event detection and 6.1% in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9% improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, IcasSP 2025

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

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：