检索结果-内蒙古大学图书馆

A Federated Learning Approach for Multi-stage Threat Analysis in Advanced Persistent Threat Campaigns

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nelles, Florian Yazdinejad, Abbas Dehghantanha, Ali Parizi, Reza M. Srivastava, Gautam The Faculty of Computer Science Deggendorf Institute of Technology Dieter-Görlitz-Platz 1 Deggendorf94469 Germany The Cyber Science Lab Canada Cyber Foundry University of Guelph ON Canada The Decentralized Science Lab Kennesaw State University GA United States The Department of Math and Computer Science Brandon University Brandon Canada The Research Centre for Interneural Computing China Medical University Taichung40402 Taiwan The Dept. of Computer Science and Math Lebanese American University Beirut1102 Lebanon

Multi-stage threats like advanced persistent threats (APT) pose severe risks by stealing data and destroying infrastructure, with detection being challenging. APTs use novel attack vectors and evade signature-based detection by obfuscating their network presence, often going unnoticed due to their novelty. Although machine learning models offer high accuracy, they still struggle to identify true APT behavior, overwhelming analysts with excessive data. Effective detection requires training on multiple datasets from various clients, which introduces privacy issues under regulations like GDPR. To address these challenges, this paper proposes a novel 3-phase unsupervised federated learning (FL) framework to detect APTs. It identifies unique log event types, extracts suspicious patterns from related log events, and orders them by complexity and frequency. The framework ensures privacy through a federated approach and enhances security using Paillier's partial homomorphic encryption. Tested on the SoTM 34 dataset, our framework compares favorably against traditional methods, demonstrating efficient pattern extraction and analysis from log files, reducing analyst workload, and maintaining stringent data privacy. This approach addresses significant gaps in current methodologies, offering a robust solution to APT detection in compliance with privacy laws. © 2024, CC BY.

关键词： Data privacy

A Hybrid Federated Learning Model for Insurance Fraud Detection

学校读者我要写书评

暂无评论

A Hybrid Federated Learning Model for Insurance Fraud Detect...

IEEE International Conference on Communications Workshops, ICC

作者： Supriya Y Nancy Victor Gautam Srivastava Thippa Reddy Gadekallu School of Information Technology and Engineering Vellore Institute of Technology Vellore Tamil Nadu India Dept. of Math and Computer Science Brandon University Brandon MB Canada

Mission-critical systems are significant for the survival of any organization. Financial systems, communication systems, and electricity grid systems are some examples of mission-critical applications. Any damage to such systems can cause business operations to fail. Insurance fraud is one of the challenges faced by mission-critical systems today. Insurance fraud detection has historically been a manual task left to claim agents, who look over the evidence and draw an inference based on their intuitions. Recently, machine learning (ML) has been predominantly used to automate the process of insurance fraud detection. Despite the success of ML models in detecting insurance fraud, privacy preservation of insured personal data continues to be a problem. To address this issue, we present a novel hybrid approach. The proposed work suggests an automated way to control the process of vehicle insurance claim fraud detection in the insurance industry. The proposed study combines Federated Learning (FL), the Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) to incorporate the advantages of each technology. The suggested model uses GA for optimal feature subset extraction. The optimized feature subset is then fed into a Federated learning with a Particle swarm optimization (FPSO) model. The findings show that the suggested hybrid model has an accuracy of 94.47% and that it may be improved even further by using other nature-inspired algorithms that are only used for fraud detection.

关键词：

SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Puglisi, Lemuel Rondinella, Alessia De Meo, Linda Guarnera, Francesco Battiato, Sebastiano Ravì, Daniele Dept. of Math and Computer Science University of Catania Catania Italy Department of Neuroinflammation University College London London United Kingdom School of Physics Engineering and CS University of Hertfordshire Hatfield United Kingdom

Brain age is a critical measure that reflects the biological ageing process of the brain. The gap between brain age and chronological age, referred to as brain PAD (Predicted Age Difference), has been utilized to investigate neurodegenerative conditions. Brain age can be predicted using MRIs and machine learning techniques. However, existing methods are often sensitive to acquisition-related variabilities, such as differences in acquisition protocols, scanners, MRI sequences, and resolutions, significantly limiting their application in highly heterogeneous clinical settings. In this study, we introduce Synthetic Brain Age (SynthBA), a robust deep-learning model designed for predicting brain age. SynthBA utilizes an advanced domain randomization technique, ensuring effective operation across a wide array of acquisition-related variabilities. To assess the effectiveness and robustness of SynthBA, we evaluate its predictive capabilities on internal and external datasets, encompassing various MRI sequences and resolutions, and compare it with state-of-the-art techniques. Additionally, we calculate the brain PAD in a large cohort of subjects with Alzheimer’s Disease (AD), demonstrating a significant correlation with AD-related measures of cognitive dysfunction. SynthBA holds the potential to facilitate the broader adoption of brain age prediction in clinical settings, where re-training or fine-tuning is often unfeasible. The SynthBA source code and pre-trained models are publicly available at https://***/LemuelPuglisi/SynthBA. © 2024, CC BY.

关键词：

Key Exchange in the Quantum Era: Evaluating a Hybrid System of Public-Key Cryptography and Physical-Layer Security

学校读者我要写书评

暂无评论

Key Exchange in the Quantum Era: Evaluating a Hybrid System ...

Annual Conference on Information sciences and Systems (CISS)

作者： Paul Staat Meik Dörpinghaus Azadeh Sheikholeslami Christof Paar Gerhard Fcllwcis Dennis Goeckel Max Planck Institute for Security and Privacy Bochum Germany Vodafone Chair Mobile Communications Systems Technische Universität Dresden Dresden Germany Math and Computer Science Department Suffolk University Boston Dept. Electrical and Computer Engineering University of Massachusetts Amherst USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

Today's information society relies on cryptography to achieve security goals such as confidentiality, integrity, authentication, and non-repudiation for digital communications. Here, public-key cryptosystems play a pivotal role to share encryption keys and create digital signatures. However, quantum computers threaten the security of traditional public-key cryptosystems as they can tame computational problems underlying the schemes, i.e., discrete logarithm and integer factorization. The prospective arrival of capable-enough quantum computers already threatens today's secret communication in terms of their long-term secrecy when stored to be later decrypted. Therefore, researchers strive to develop and deploy alternative *** this work, we evaluate a key exchange protocol based on combining public-key schemes with physical-layer security, anticipating the prospect of quantum attacks: If a powerful quantum attacker cannot immediately obtain a private key, legitimate parties have a window of short-term secrecy to perform a physical-layer jamming key exchange (JKE) to establish a long-term shared secret. Thereby, the protocol constraints the computation time available to the attacker to break the employed public-key cryptography. In this paper, we outline the protocol, discuss its security, and point out challenges to be resolved.

关键词： computers Protocols Quantum computing Quantization (signal) Non-repudiation Public key cryptography Security Time factors Jamming Signal resolution

AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogeneous Knowledge Representations

学校读者我要写书评

暂无评论

AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogene...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alain Bertrand Bomgni Ribot Fleury Téné Ceskoutsé Kevin Jordan Njike Njingang Thomas Bouetou Bouetou Venkataramana Gadhamshetty Etienne Gnimpieba Z. Math Science and Technology Oglala Lakota College Kyle SD USA Ecole Nationale Supérieure Polytechnique University of Yaounde 1 Yaounde Cameroon Dept. of Computer Science University of Dschang Dschang Cameroon Dept. of Civil and Environmental Engineering South Dakota School of Mines and Technology Rapid City SD USA Dept. of Biomedical Engineering University of South Dakota Vermillion SD USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The synthesis of small molecules is a crucial task across multiple scientific domains, including drug discovery, materials science, and sustainable chemistry. As AI and Machine Learning (ML) continue to advance, these technologies offer transformative potential in molecular synthesis, enhancing efficiency and expanding synthetic possibilities. In particular, small molecule synthesis has profound implications for creating novel therapeutic agents, high-performance materials, and greener chemical processes, but a major challenge remains in designing efficient synthetic routes for target molecules. Retrosynthesis, the process of mapping out synthetic pathways by working backwards from a target molecule, represents a vital step; however, traditional retrosynthesis methods often struggle to predict complex or novel transformations. To address this limitation, we introduce AIM-HKR: AI-Driven Molecular Retrosynthesis Using Heterogeneous Knowledge Representations, a model that leverages graph neural network techniques to enhance retrosynthetic predictions. AIM-HKR integrates information from heterogeneous knowledge graphs, capturing the intricate relationships and analogical reasoning required for retrosynthesis. This model generates type-specific embeddings that reflect both network topology and semantic connections across different entity types, such as molecules, reactions, and functional groups. AIM-HKR’s unique capacity to leverage heterogeneous graphs allows it to propose synthetic pathways that extend beyond established precedents, enabling predictions of chemically feasible but previously uncharted transformations. We believe AIM-HKR has the potential to significantly advance molecular synthesis through AI-driven retrosynthesis, establishing a new paradigm in AI-assisted chemistry.

关键词： Technological innovation Chemistry Accuracy Scalability Semantics Machine learning Predictive models Reliability engineering Drug discovery Chemicals

Threshold Decision-Making Dynamics Adaptive to Physical Constraints and Changing Environment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Amorim, Giovanna Santos, María Park, Shinkyu Franci, Alessio Leonard, Naomi Ehrich The Dept. of Mechanical and Aerospace Engineering Princeton Univ. PrincetonNJ08544 United States Computer Electrical and Math. Science and Eng. Div. Thuwal23955-6900 Saudi Arabia The Department of Electrical Engineering and Computer Science University of Liege 10 Allée de la Découverte Liège4000 Belgium The WEL Research Institute Wavre Belgium

We propose a threshold decision-making framework for controlling the physical dynamics of an agent switching between two spatial tasks. Our framework couples a nonlinear opinion dynamics model that represents the evolution of an agent’s preference for a particular task with the physical dynamics of the agent. We prove the bifurcation that governs the behavior of the coupled dynamics. We show by means of the bifurcation behavior how the coupled dynamics are adaptive to the physical constraints of the agent. We also show how the bifurcation can be modulated to allow the agent to switch tasks based on thresholds adaptive to environmental conditions. We illustrate the benefits of the approach through a multi-robot task allocation application for trash collection. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamics

Federated Learning for the Metaverse: A Short Survey

学校读者我要写书评

暂无评论

Federated Learning for the Metaverse: A Short Survey

Intelligent Metaverse Technologies & Applications (iMETA), International Conference on

作者： Gokul Yenduri Dasaradharami Reddy K Gautam Srivastava Supriya Y Ramalingam M Thippa Reddy Gadekallu Feras M. Awaysheh Vellore Instituite of Technology Vellore Tamil Nadu India Dept. of Math and Computer Science Brandon University Brandon Canada Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Delta Research Center Institute of Computer Science Tartu University Tartu Estonia

The Metaverse, a 3-dimensional virtual realm mirroring real-world objects, promises transformative experiences. Its potential is tempered by data collection, confidentiality, and privacy concerns. In tandem with AI-enabled technologies, edge computing can provide a practical solution to overcoming many of these challenges. This paper argues that combining AI-enabled technologies with edge computing-specifically via federated learning (FL) can address these challenges. FL, as a privacy-centric distributed machine learning (ML) approach, enables knowledge sharing among Metaverse clients without compromising user data. However, while FL posits potential resolutions for the Metaverse, a discernible lacuna remains in the comprehensive study of its overarching consequences. The literature misses an extensive study of adopting these new deployment architectures, giving it significant research impact. This paper bridges this knowledge gap, exploring the symbiosis between the Metaverse and FL. We first introduce the foundational concepts of both domains and detail enabling technologies such as digital twins, the Internet of Things, brain-computer interfaces, blockchain, and extended reality. Next, we delve into practical applications of FL within the metaverse, spanning sectors like healthcare, education, e-commerce, gaming, and the military. Finally, the paper highlights the key challenges and future directions for integrating FL within the metaverse ecosystem.

关键词：

Sustainable Flood Risk Identification and Assessment Using Artificial Intelligence: A Literature Review and Case Scenario

学校读者我要写书评

暂无评论

Sustainable Flood Risk Identification and Assessment Using A...

Public Safety Technology (WFPST), IEEE World Forum on

作者： Imran Ahmed Misbah Ahmad Abdellah Chehri Gwanggil Joen School of Comp.Inf. Science Anglia Ruskin University Cambridge UK University of the West of Hartpury and University Bristol and Gloucester UK Dept. Math. Comp. Science Royal Military College of Canada Kingston Canada Dep. of Elect. Com. Eng. Incheon National University Incheon Korea

ISBN: (数字)9798350329148

ISBN: (纸本)9798350329155

The combination of Internet of Things (IoT) and Artificial Intelligence (AI) has been widely applied in various fields, including transportation, agriculture, tourism, smart cities, environmental monitoring, and security. The growing accessibility of satellite and drone imagery, as well as remote sensing data, such as drones, has enabled the efficient utilization and training of deep learning algorithms. These algorithms can accurately identify, categorize, and partition flood areas in real-time. By integrating artificial intelligence (Al)-powered flood detection algorithms with additional data sources, such as meteorological forecasts and ground-based sensors, it is possible to create robust flood monitoring systems. These systems can offer timely alerts for potential flood events and enable efficient emergency response measures. The paper outlines advanced functionalities and technologies that will be available by integrating the Internet of Things (IoT) and Artificial Intelligence (AI) for flood monitoring. The paper provides a comprehensive overview of AI-IoT visions, services, applications, and the networking infrastructure involved. Additionally, it includes a vast assortment of satellite images.

关键词： Deep learning Image segmentation Weather forecasting Real-time systems Satellite images Partitioning algorithms Floods

Drop the GAN: In defense of patches nearest neighbors as Single image generative models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Granot, Niv Feinstein, Ben Shocher, Assaf Bagon, Shai Irani, Michal Dept. of Computer Science and Applied Math The Weizmann Institute of Science

Single image generative models perform synthesis and manipulation tasks by capturing the distribution of patches within a single image. The classical (pre Deep Learning) prevailing approaches for these tasks are based on an optimization process that maximizes patch similarity between the input and generated output. Recently, however, Single Image GANs were introduced both as a superior solution for such manipulation tasks, but also for remarkable novel generative tasks. Despite their impressiveness, single image GANs require long training time (usually hours) for each image and each task. They often suffer from artifacts and are prone to optimization issues such as mode collapse. In this paper, we show that all of these tasks can be performed without any training, within several seconds, in a unified, surprisingly simple framework. We revisit and cast the "good-old" patch-based methods into a novel optimization-free framework. We start with an initial coarse guess, and then simply refine the details coarse-to-fine using patch-nearest-neighbor search. This allows generating random novel images better and much faster than GANs. We further demonstrate a wide range of applications, such as image editing and reshuffling, retargeting to different sizes, structural analogies, image collage and a newly introduced task of conditional inpainting. Not only is our method faster (×103-×104 than a GAN), it produces superior results (confirmed by quantitative and qualitative evaluation), less artifacts and more realistic global structure than any of the previous approaches (whether GAN-based or classical patch-based). © 2021, CC BY.

关键词： Nearest neighbor search