检索结果-内蒙古大学图书馆

An ensemble deep learning based IDS for IoT using Lambda architecture

Cybersecurity 2023年第3期6卷 1-17页

作者： Rubayyi Alghamdi Martine Bellaiche Computer and Software Engineering Department école PolytechniqueMontrealCanada

The Internet of Things(IoT)has revolutionized our world today by providing greater levels of accessibility,connectivity and ease to our everyday *** enables massive amounts of data to be traversed across multiple heterogeneous devices that are all *** phenomenon makes IoT networks vulnerable to various network attacks and *** an Intrusion Detection System(IDS)for IoT networks is challenging as they enable a massive amount of data to be aggregated,which is difficult to handle and analyze in real time mainly because of the heterogeneous nature of IoT *** inefficient,traditional IDS approach accentuates the need to develop advanced IDS techniques by employing Machine or Deep *** paper presents a deep ensemble-based IDS using Lambda architecture by following a multi-pronged classification *** classification uses Long Short Term Memory(LSTM)to differentiate between malicious and benign traffic,while the multi-class classifier uses an ensemble of LSTM,Convolutional Neural Network and Artificial Neural Network classifiers to detect the type of *** model training is performed in the batch layer,while real-time evaluation is carried out through model inferences in the speed layer of the Lambda *** proposed approach gives high accuracy of over 99.93%and saves useful processing time due to the multi-pronged classification strategy and using the lambda architecture.

关键词： IoT IDS Lambda architecture Cyber-attacks Deep learning Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Synergy: Leveraging RIS and Reinforcement Learning for Secure, Adaptive Underlay Cognitive Radio Networks 15

Dynamic Synergy: Leveraging RIS and Reinforcement Learning f...

引用

15th Global Information Infrastructure and Networking Symposium, GIIS 2025

作者： Tashman, Deemah H. Cherkaoui, Soumaya Polytechnique Montreal Department of Computer and Software Engineering Montreal Canada

ISBN: (纸本)9798331520113

Reconfigurable intelligent surfaces (RISs) have recently been employed to facilitate communication and improve performance by reflecting signals through configuring phase shifts toward the intended destination. This article examines the physical layer security of an underlay cognitive radio network aided by an RIS and in the presence of multiple eavesdroppers. The research is conducted under practical conditions, encompassing RIS hardware constraints and cascaded fading channels. An optimization problem is proposed with the objective of maximizing the secrecy rate of secondary users by optimizing the reflection angles of the RIS and the transmission power of the secondary user transmitter. A deep reinforcement learning method, specifically the soft actor-critic, is presented as a solution. The results section demonstrates the effect of altering the number of RIS elements on security. We also analyze the impact of hardware limitations and cascade levels on the secrecy rate. The effect of varying the number of eavesdroppers and the maximum permissible transmission power are also examined. © 2025 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Exploration of the Possibility for a Wider Range of the Discount Factor for Reinforcement Learning 6

Exploration of the Possibility for a Wider Range of the Disc...

引用

6th International Conference on Communications, Information System and computer engineering, CISCE 2024

作者： Li, Monica M.Q. Polytechnique Montreal Department of Computer and Software Engineering Montreal Canada

ISBN: (纸本)9798350353174

The discount factor for reinforcement learning has been constrained to the range [0, 1] to avoid overestimation of state values during training. Although theoretical studies have indicated that discount factors greater than 1 could be valid for certain tasks, experimental work has generally maintained the [0, 1] limit in flexible discount factor optimization. Our study explores the impact of allowing discount factors to exceed 1 across a variety of reinforcement learning algorithms and classic training environments. Our findings demonstrate that in some grid-based environments, reinforcement learning algorithms with discount factors above 1 can achieve comparable performance to those with discount factors within the [0, 1] range. However, performance tends to be more variable when the discount factor exceeds 1. © 2024 IEEE.

关键词： discount factor reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Open RAN Slicing with Quantum Optimization 15

Open RAN Slicing with Quantum Optimization

引用

15th Global Information Infrastructure and Networking Symposium, GIIS 2025

作者： Keyela, Patatchona Cherkaoui, Soumaya Polytechnique Montreal Computer Engineering and Software Engineering Dept. Montreal Canada

ISBN: (纸本)9798331520113

RAN slicing technology is a key aspect of the Open RAN paradigm, allowing simultaneous and independent provision of various services such as ultra-reliable low-latency communications (URLLC), enhanced mobile broadband (eMBB), and massive machine-type communications (mMTC) through virtual networks that share a single radio access infrastructure. Efficient resource allocation is crucial for RAN slicing, as each service has specific quality of service (QoS) requirements, and a balance between different services must be maintained. Although heuristic and reinforcement learning (RL) techniques have been explored to achieve efficient resource allocation, these approaches face notable limitations: heuristic algorithms face complexity issues that limit their effectiveness in large networks, RL solutions are constrained by their dependency on training data and struggle to adapt to new scenarios and environments. This paper proposes a framework that leverages quantum optimization techniques to optimize radio resource blocks allocation in Open RAN slicing for URLLC and eMBB services. We provide a classical problem formulation and the quantum implementation using the constrained quadratic model on Dwave quantum annealing platform, showcasing the potential of quantum optimization techniques to deliver in real-time optimal solutions for optimization problems in 5G and beyond networks. © 2025 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Emergency events detection based on integration of federated learning and active learning

引用

International Journal of Information Technology (Singapore) 2023年第6期15卷 2863-2876页

作者： Alfalqi, Khalid Bellaiche, Martine Computer and Software Engineering Department Ecole Polytechnique Montreal Canada

Social media networks now make it easy to access, in real-time, massive amounts of information from all over the world. They are often the primary source of information for billions of people. In addition to other uses, social media platforms can be valuable to provide real-time information about emergency events and can help detect emergency situations. This can provide affected individuals with crucial information about imminent dangers, prompting them to take appropriate action and significantly influencing their decisions. The continuous flow of data generated during these emergencies requires efficient training and modeling. Deep learning can simplify this process and make it less reliant on feature extraction strategies. However, implementing deep learning-based solutions can be expensive and time-consuming due to the vast amounts of data involved. To address these limitations, in this paper, we employed and analyzed the effectiveness of utilizing Active Learning techniques along with Federated Learning for emergency events using a dataset garnered from the social media. After collecting images, we used a Federated Learning paradigm to split the data amongst different clients and used vision transformers as local models for each client. Furthermore, we used an ensemble approach to integrate the results from these strengthened local and global models in a novel way, demonstrating that the proposed setup yields an accuracy of 99%. The Logloss score reached 0.043, indicating the outstanding performance of our approach. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Active learning Emergency event detection Federated learning Object detection Snapchat Social networks Twitter Vision transformers ViT

来源：评论

学校读者我要写书评

暂无评论

Advancing Formal Verification: Fine-Tuning LLMs for Translating Natural Language Requirements to CTL Specifications 35

Advancing Formal Verification: Fine-Tuning LLMs for Translat...

引用

35th International Workshop on Rapid System Prototyping, RSP 2024

作者： Zrelli, Rim Misson, Henrique Amaral Ben Attia, Maroua De Magalhaes, Felipe Gohring Shabah, Abdo Nicolescu, Gabriela Polytechnique Montreal Computer Engineering and Software Engineering Department Montreal Canada Research and Development Humanitas Solutions Montreal Canada

ISBN: (纸本)9798331519537

In the domain of formal verification, translating natural language (NL) requirements into Computation Tree Logic (CTL) specifications presents a notable challenge due to the disparity between human-readable documents and formal specifications. This paper introduces a novel approach that leverages Large Language Models (LLMs) to automate this translation process, thereby enhancing the accuracy and efficiency of formal verification practices. We fine-tune three state-of-the-art LLMs - LLAMA3, Mistral, and Qwen2 - with a particular focus on optimizing the Mistral model due to its superior performance. Our methodology is supported by the Natural2CTL dataset, consisting of 2,095 NL requirements and their corresponding CTL specifications. We employ evaluation metrics such as validation loss, accuracy, semantic similarity, and Structural Operator Jaccard Similarity (SOJS) for a comprehensive assessment of model performance. Additionally, a comparative analysis with human translators, trained in CTL logic, underscores the LLMs' potential to match or even surpass human accuracy in translating NL requirements into formal specifications. Our findings reveal that the fine-tuned Mistral model significantly outperforms the other LLMs and human participants, demonstrating superior accuracy in generating CTL specifications. This study advances the field of formal verification by proposing a scalable solution to the NL-to-CTL translation challenge, setting a new benchmark for the integration of AI tools in complex specification tasks. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Motivating Users to Atend to Privacy: A Theory-Driven Design Study

Motivating Users to Atend to Privacy: A Theory-Driven Design...

引用

2024 ACM Designing Interactive Systems Conference, DIS 2024

作者： Shiri, Varun Xiong, Maggie Cheng, Jinghui Guo, Jin L.C. Department of Computer and Software Engineering Polytechnique Montreal MontrealQC Canada School of Computer Science McGill University MontrealQC Canada

ISBN: (纸本)9798400705830

In modern technology environments, raising users’ privacy awareness is crucial. Existing eforts largely focused on privacy policy presentation and failed to systematically address a radical challenge of user motivation for initiating privacy awareness. Leveraging the Protection Motivation Theory (PMT), we proposed design ideas and categories dedicated to motivating users to engage with privacy-related information. Using these design ideas, we created a conceptual prototype, enhancing the current App Store product page. Results from an online experiment and follow-up interviews showed that our design efectively motivated participants to attend to privacy issues, raising both the threat appraisal and coping appraisal, two main factors in PMT. Our work indicated that efective design should consider combining PMT components, calibrating information content, and integrating other design elements, such as visual cues and user familiarity. Overall, our study contributes valuable design considerations driven by the PMT to amplify the motivational aspect of privacy communication. © 2024 Copyright held by the owner/author(s).

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Implementing and Evaluating a P4-based Access Gateway Function on a Tofino Switch 6

Implementing and Evaluating a P4-based Access Gateway Functi...

引用

6th International Conference on Advanced Communication Technologies and Networking, CommNet 2023

作者： Makhroute, El-Mehdi Elharti, Mohammed-Ayoub Brouillard, Vincent Savaria, Yvon Ould-Bachir, Tarek Polytechnique Montréal Department of Computer and Software Engineering Montreal Canada Polytechnique Montréal Department of Electrical Engineering Montreal Canada

ISBN: (纸本)9798350329391

This paper introduces an Access Gate Function (AGF) that has been implemented using the P4 language and evaluates its performance when running on a Tofino switch. Through the process of translating specifications from the Broadband Forum (BBF) for Fixed Mobile Convergence in the 5G Core into a P4 code and by conducting data plane simulations on software switch models, we provide evidence that the AGF solution conforms to industry standards and exhibits efficient and scalable performance characteristics. Subsequently, we assess the prototype's implementation on a Tofino switch, analyzing its capabilities and limitations. The reported results demonstrate that the programmable P4 Tofino switch efficiently handles a significant number of sessions, further reinforcing the potential and practicality of the proposed solution for industrial deployment in fixed-mobile convergence scenarios. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Defense Against Model Stealing Attacks on Convolutional Neural Networks 22

Efficient Defense Against Model Stealing Attacks on Convolut...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Khaled, Kacem Dhaouadi, Mouna De Magalhaes, Felipe Gohring Nicolescu, Gabriela Polytechnique Department of Computer Engineering and Software Engineering Montreal Canada University of Montreal Department of Computer Science and Operations Research Canada

ISBN: (纸本)9798350345346

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The current state-of-the-art defenses against model stealing attacks suggest adding perturbations to the prediction probabilities. However, they suffer from heavy computations and make impracticable assumptions about the adversary. They often require the training of auxiliary models. This can be time-consuming and resource-intensive which hinders the deployment of these defenses in real-world applications. In this paper, we propose a simple yet effective and efficient defense alternative. We introduce a heuristic approach to perturb the output probabilities. The proposed defense can be easily integrated into models without additional training. We show that our defense is effective in defending against three state-of-the-art stealing attacks. We evaluate our approach on large and quantized (i.e., compressed) Convolutional Neural Networks (CNNs) trained on several vision datasets. Our technique outperforms the state-of-the-art defenses with a ×37 faster inference latency without requiring any additional model and with a low impact on the model's performance. We validate that our defense is also effective for quantized CNNs targeting edge devices. © 2023 IEEE.

关键词： Deep learning Model stealing attacks Privacy Quantization Security

来源：评论

学校读者我要写书评

暂无评论

DevDynaP: A Dynamic Local Community Detection Algorithm

引用

SN computer Science 2025年第4期6卷 1-11页

作者： Bakhtar, Sahar Harutyunyan, Hovhannes A. Department of Computer Science and Software Engineering Concordia University Montreal Canada

Recent years have witnessed the rapid growth of social network services. Real-world social networks are huge and changing over time. Consequently, the problems in this area have become more complex. Community detection is one of the most important problems in social networks. A good community can be defined as a group of nodes that are highly connected to each other and loosely connected to the nodes outside the community. Regarding the fact that social networks are huge in size, having complete information about the whole network is almost impossible. As a result, the problem of local community detection has become more popular in recent years. However, the problem of community detection in dynamic networks is well-investigated, the local community detection is not widely addressed by researchers in dynamic networks. In this paper, a dynamic local community detection algorithm is proposed. The purpose of the proposed algorithm is to explore the network as fast as possible and detect communities as well. Experimental results show that the proposed algorithm discovers the unknown parts of networks faster than similar algorithms. Also, the detected communities by the proposed algorithm outperform that of the compared algorithm in different snapshots. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Dynamic social network Geodesic distance metric Local community detection Modularity

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：