检索结果-内蒙古大学图书馆

Proceedings - 2024 22nd International Symposium on Network computing and Applications, NCA 2024 2024年 xi页

作者： Stabili, Dario Tricomi, Giuseppe Alma Mater Studiorum - University of Bologna Italy Institute for High Performance Computing and Networking ICAR CNR Napoli Italy

来源：评论

学校读者我要写书评

暂无评论

ORISHA: Improving Threat Detection through Orchestrated Information Sharing 31

ORISHA: Improving Threat Detection through Orchestrated Info...

引用

31st Symposium of Advanced Database Systems, SEBD 2023

作者： Caviglione, Luca Comito, Carmela Guarascio, Massimo Manco, Giuseppe Pisani, Francesco Sergio Zuppelli, Marco Institute for Applied Mathematics and Information Technologies Via de Marini 6 Genova16149 Italy Institute for High Performance Computing and Networking Via P. Bucci 8-9/C Rende87036 Italy

The exponential growth in the number of cyber threats requires sharing in a timely and efficient manner a wide range of Indicators of Compromise (IoCs), i.e., fragments of forensics data that can be used to recognize malicious network or system activities. To this aim, a suitable architecture is required, especially to distribute and process the various IoCs. Unfortunately, the continuous creation of offensive techniques, along with the diffusion of advanced persistent threats, imposes the ability to update and extend the platform used to manage the multitude of IoCs collected in the wild. In this paper, we present the ORISHA architecture, which takes advantage of a distributed threat detection system to match performance and scalability requirements. The paper also discusses how the platform can be extended to handle the most recent "stealthy" malware as well as campaigns aimed at spreading fake news. © 2023 CEUR-WS. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Community Detection in Dense Networks using Effective Resistance and Link Pruning

Community Detection in Dense Networks using Effective Resist...

引用

International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)

作者： Annalisa Socievole Clara Pizzuti National Research Council of Italy (CNR) Institute for High Performance Computing and Networking Rende Italy

The detection of communities in networks can be made more effective by weighting edges with a distance measure reflecting the similarity/dissimilarity between pairs of nodes. In this paper, we focus on a particular measure derived from the fields of electrical circuits: the effective resistance. Specifically, we propose a community detection method organized into two phases. During the first phase, the edges of the input graph are weighted through their effective resistance and a weight thresholding sparsification procedure is applied to cut the less important edges while keeping the edges fundamental for maintaining a modular structure. We then run a GA-based community detection method maximizing the modularity as the objective function on the sparse graph. The results of the experiments over both real-world and synthetically generated networks show the effectiveness of the approach when compared to other benchmark methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of Histology Images Based on a Compact 3D Representation 1

引用

15th International Conference on Pattern Recognition and Information Processing, PRIP 2021

作者： Brancati, Nadia Cicala, Crispino Frucci, Maria Riccio, Daniel Institute for High Performance Computing and Networking National Research Council of Italy Naples Italy Computer Scientist Milan Italy University "Federico II" Naples Italy

ISBN: (数字)9783030988838

ISBN: (纸本)9783030988821

Although the Convolutional Neural Networks (CNNs) have been widely adopted for the classification of histopathology images, one of the main drawbacks of CNNs is their inability to cope with gigapixel images. To deal with the high resolution of Whole Slide Image (WSI), many methods focus on patch processing which can result in improper representation if the patches are analyzed independently, losing the context information that is fundamental in digital pathology. In this study, the WSI is mapped into a compressed representation preserving the topological and morphological information relating to spatial correlations of neighboring patch features of the WSI. Such a representation is used to train a CNN to solve a classification task of breast histological images. The effectiveness of the suggested framework is demonstrated through experiments on Camelyon16 dataset. The results show the performance of our approach when three different ways to incorporate the spatial correlation in the tensor are used singly or in combination, highlighting that it is comparable with the state of the art. © 2022, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Evaluating Retrieval-Augmented Generation for Question Answering with Large Language Models

Evaluating Retrieval-Augmented Generation for Question Answe...

引用

2024 Ital-IA Intelligenza Artificiale - Thematic Workshops, Ital-IA 2024

作者： Oro, Ermelinda Granata, Francesco Maria Lanza, Antonio Bachir, Amir De Grandis, Luca Ruffolo, Massimo National Research Council Institute for High Performance Computing and Networking via P. Bucci 8/9C CS Rende87036 Italy Altilia srl TechNest Start-up Incubator of University of Calabria Piazza Vermicelli CS Rende87036 Italy

We present a comprehensive framework for evaluating retrieval-augmented generation (RAG) systems designed for question-answering tasks using large language models (LLMs). The proposed framework integrates document ingestion, information retrieval, answer generation, and evaluation phases. Both ground truth-based and reference-free evaluation metrics are implemented to provide a multi-faceted assessment approach. Through experiments across diverse datasets like NarrativeQA and a proprietary financial dataset (FinAM-it), the reliability of existing metrics is investigated by comparing them against rigorous human evaluations. The results demonstrate that ground truth-based metrics such as BEM and RAGAS Answer Correctness exhibit a moderately strong correlation with human judgments. However, reference-free metrics still struggle to capture nuances in answer quality without predefined correct responses accurately. An in-depth analysis of Spearman correlation coefficients sheds light on the interrelationships and relative effectiveness of various evaluation approaches across multiple domains. While highlighting the current limitations of reference-free methodologies, the study underscores the need for more sophisticated techniques to better approximate human perception of answer relevance and correctness. Overall, this research contributes to ongoing efforts in developing reliable evaluation frameworks for RAG systems, paving the way for advancements in natural language processing and the realization of highly accurate and human-like AI systems. © 2024 Copyright for this paper by its authors.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligence Model for Securing Healthcare Ecosystem 13th

Swarm Intelligence Model for Securing Healthcare Ecosystem

引用

13th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN / The 12th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, ICTH 2022 / Affiliated Workshops

作者： Ribino, Patrizia Ciampi, Mario Islam, Shareeful Papastergiou, Spyridon Institute for High Performance Computing and Networking National Research Council of Italy Italy School of Computing and Information Science Anglia Ruskin University United Kingdom Department of Informatics University of Piraeus Greece Focal Point Belgium

The healthcare sector is constantly facing challenges in ensuring security due to the sophisticated attacks by the threat actor for acquiring sensitive patient data. An attack on the system can pose any potential risk to the business continuity. The increased use of information technology in the modern healthcare system makes medical devices and systems more vulnerable to exploitation and possible cyber-security attacks. This paper proposes a flexible and decentralized cyber-security model based on the integration of multi-agent systems and swarm intelligence for tackling the propagation of attacks inside interconnected healthcare organizations and ensuring the whole healthcare ecosystem's security and resilience. The proposed model is based on the collaboration between the agents with different functions and cognitive capabilities, named primary and supervisor agents. Primary agents are lightweight BDI (Belief-Desire-Intention) agents implementing a minimum set of capabilities for monitoring a specific area of the healthcare system;supervisor agents incorporate an extended version of the BDI reasoning to provide advanced capabilities for securing the overall healthcare system by enabling collective intelligence and overall cyber-security awareness. The preliminary experimental results show that the model is robust and responsive for securing the ecosystem. © 2022 Elsevier B.V.. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Cyber threat assessment and management for securing healthcare ecosystems using natural language processing

Cyber threat assessment and management for securing healthca...

引用

作者： Silvestri, Stefano Islam, Shareful Amelin, Dmitry Weiler, Gabriele Papastergiou, Spyridon Ciampi, Mario Institute for High Performance Computing and Networking of the National Research Council of Italy ICAR-CNR Via Pietro Castellino 111 Naples80131 Italy School of Computing and Information Science Anglia Ruskin University Cambridge United Kingdom Focal Point Waterloo Belgium Department of Informatics University of Piraeus Piraeus Greece Fraunhofer Institute for Biomedical Engineering IBMT Sulzbach Germany

The healthcare sectors have constantly faced significant challenge due to the rapid rise of cyber threats. These threats can pose any potential risk within the system context and disrupt the critical healthcare service delivery. It is therefore necessary for the healthcare organisations to understand and tackle the threats to ensure overall security and resilience. However, threats are continuously evolved and there is large amount of unstructured security-related textual information is available. This makes the threat assessment and management task very challenging. There are a number of existing works that consider Machine Learning models for detection and prediction of cyber attack but they lack of focus on the Natural Language Processing (NLP) to extract the threat information from unstructured security-related text. To this end, this work proposes a novel method to assess and manage threats by adopting natural language processing. The proposed method has been tailored for the healthcare ecosystem and allows to identify and assess the possible threats within healthcare information infrastructure so that appropriate control and mitigation actions can be taken into consideration to tackle the threat. In detail, NLP techniques are used to extract the useful threat information related to specific assets of the healthcare ecosystems from the largely available security-related information on Internet (e.g. cyber security news), to evaluate the level of the identified threats and to select the required mitigation actions. We have performed experiments on real healthcare ecosystems in Fraunhofer Institute for Biomedical Engineering, considering in particular three different healthcare scenarios, namely implantable medical devices, wearables, and biobank, with the purpose of demonstrating the feasibility of our approach, which is able to provide a realistic manner to identify and assess the threats, evaluate the threat level and suggest the required mitigation actions. ©

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Super-Resolution in Medical Imaging

Cross-domain Super-Resolution in Medical Imaging

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Vincenzo Bevilacqua Antonio Di Marino Emanuel Di Nardo Angelo Ciaramella Ivanoe De Falco Giovanna Sannino Institute for High-Performance Computing and Networking (ICAR) - National Research Council (CNR) Naples Italy University of Naples Parthenope Naples Italy

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

The use of Super-Resolution SR algorithms applied to Magnetic Resonance Images (MRIs) is increasingly common in the medical field. Increasing the resolution of images allows physicians to more easily observe image details. Over the years, several SR approaches have been tried by researchers. Among the various approaches, Diffusion Models (DMs) have been shown to perform well in the SR task. In this work, we propose the use of a Latent Diffusion Model (LDM) for the SR of medical images. Different studies have shown that LDMs improve the performance of DMs in several SR tasks. To our knowledge, LDMs have not been tested for SR of medical images such as MRIs. We therefore perform fine-tuning of an LDM on medical datasets. To evaluate the SR images generated by the LDM, we compare them to the original high-resolution images using two similarity measurements. We show that the LDM achieves better similarity values than other SR models on the same medical dataset. We also show with visual examples the advantage of applying SR using an LDM.

关键词： Computers Visualization Shape Magnetic resonance imaging Computational modeling Superresolution Magnetic resonance Medical services Diffusion models Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Application of Federated Learning Approaches for Time-Series Classification in eHealth Domain

引用

Procedia Computer Science 2022年 207卷 3545-3552页

作者： Giovanni Paragliola National Research Council (CNR) - Institute for High-Performance Computing and Networking (ICAR) Italy Naples

Contemporary Machine Learning approaches (e.g., Deep Learning) need huge volumes of data to build accurate and robust statistical models. Nowadays, such data are often collected by distinct and geographically distributed entities and successively transmitted to and stored by centralized nodes that implement the learning process. However, this approach exposes data to security and privacy issues during the transmitting process. In order to demonstrate the benefits which Federate learning can bring concerning these issues, this paper proposes an application of the Federated Learning approach to training a time series (TS)-based model for the early identification of the level of risk associated with patients with hypertension in a federated healthcare environment. The results demonstrate the goodness of the solution in comparison with traditional centralized approaches. The solution achieves good results; indeed, the accuracy is over 0.90%. The goodness of the model is also confirmed by the values of recall and precision, equal to 82% and 96%, respectively

关键词： Federated Learning Self-Adaptive Systems Time Series Analysis Classification Communication Costs Healthcare Informatics

来源：评论

学校读者我要写书评

暂无评论

Generative Methods for Out-of-distribution Prediction and Applications for Threat Detection and Analysis: A Short Review 1st

Generative Methods for Out-of-distribution Prediction and Ap...

引用

1st International Workshop on Digital Sovereignty in Cyber Security: New Challenges in Future Vision, CyberSec4Europe 2022

作者： Coppolillo, Erica Liguori, Angelica Guarascio, Massimo Pisani, Francesco Sergio Manco, Giuseppe Department of Mathematics and Computer Science University of Calabria Rende Italy Department of Computer Engineering Modeling Electronics an d Systems University of Calabria Rende Italy Institute for High Performance Computing and Networking of Italian National Research Council Rende Italy

ISBN: (纸本)9783031360954

In recent times, Machine Learning has played an important role in developing novel advanced tools for threat detection and mitigation. Intrusion Detection, Misinformation, Malware, and Fraud Detection are just some examples of cybersecurity fields in which Machine Learning techniques are used to reveal the presence of malicious behaviors. However, Out-of-Distribution, i.e., the potential distribution gap between training and test set, can heavily affect the performances of the traditional Machine Learning based methods. Indeed, they could fail in identifying out-of-samples as possible threats, therefore devising robust approaches to cope with this issue is a crucial and relevant challenge to mitigate the risk of undetected attacks. Moreover, a recent emerging line proposes to use generative models to yield synthetic likely examples to feed the learning algorithms. In this work, we first survey recent Machine Learning and Deep Learning based solutions to face both the problems, i.e., outlier detection and generation;then we illustrate the main cybersecurity application scenarios in which these approaches have been adopted successfully. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

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：