Workshops

Session AidTSP-TS1: AidTSP Technical Session I Session AidTSP-TS2: AidTSP Technical Session II Session AidTSP-TS3: AidTSP Technical Session III Session AidTSP-TS4: AidTSP Technical Session IV
Session AoI-Open: Opening Session Session AoI-Key: Keynote Session AoI-SCH: Scheduling and Optimization for AoI Session AoI-CBrk: Virtual Coffee Break Session AoI-BEY: Beyond AoI Metrics
Session CNERT-O: Opening Session Session CNERT-K: Keynote Session CNERT-P: Panel Session CNERT-S1: Session 1, Experimentation Enabling Capabilities Session CNERT-S2: Session 2, Services and network design Session CNERT-S3: Session 3, Wireless Session CNERT-D: Demo Session
Session DeepWireless-OS: Opening Session Session DeepWireless-KS1: Keynote Session 1 Session DeepWireless-TS1: Technical Session 1 - Deep Learning for Wireless Security Session DeepWireless-TS2: Technical Session 2 - Deep Learning for Wireless Applications Session DeepWireless-KS2: Keynote Session 2 Session DeepWireless-TS3: Technical Session 3 - Deep Learning for 5G Communications Session DeepWireless-CS: Closing Session
Session DroneCom-TS1: Technical Session I Session DroneCom-KS1: Keynote Session I Session DroneCom-TS2: Technical Session II Session DroneCom-TS3: Technical Session III Session DroneCom-KS2: Keynote Session II Session DroneCom-TS4: Technical Session IV
Session FOGML-S1: Opening Remarks Session FOGML-S2: Federated Learning Session FOGML-S3: Distributed Learning and Edge Computing
Session GI-00: Session#0 - Opening Session with Invited Keynote Session GI-01: Session#1 - Applying Machine Learning to Next Generation Internet Session GI-02: Session#2 - Performance Optimization of Next Generation Internet
Session ICCN-KS1: Security in Wireless Body Area Networks Session ICCN-B1: Virtual Coffee Break Session ICCN-S1: Cloud and Edge Computing Session ICCN-S2: Cloud and Edge Security Session ICCN-B2: Virtual Lunch Break Session ICCN-S3: Cloud and Edge Computing Session ICCN-S4: Cloud and Edge Computing
Session MobiSec-S1: AI & Security (I) Session MobiSec-K: Keynote: AI for Cybersecurity and Security of AI Session MobiSec-S2: AI & Security (II) Session MobiSec-S3: Mobile & Edge Security Session MobiSec-S4: Communication Security
Session NG-OPERA-OS: Opening Session Session NG-OPERA-KS: Keynote Session Session NG-OPERA-PS: Panel Session Session NG-OPERA-Break-1: Break Session NG-OPERA-TS1: Technical Session 1: Machine Learning and Resource Optimization for 6G RANs Session NG-OPERA-Lunch: Lunch Session NG-OPERA-TS2: Technical Session 2: System-level Solutions for Open RANs Session NG-OPERA-Break-2: Break Session NG-OPERA-TS3: Technical Session 3: Non-terrestrial Integration and Posters Session NG-OPERA-ACS: Awards and Closing
Session NetSciQCom-S1: Keynote Talk Session NetSciQCom-S2: Contributed Talks
Session PerAI-6G-Opening: Opening Session Session PerAI-6G-Keynote-1: Keynote Session 1 Session PerAI-6G-Keynote-2: Keynote Session 2 Session PerAI-6G-Session-1: Session 1: AI applications in 6G Session PerAI-6G-Session-2: Session 2: Distributed Learning in 6G Session PerAI-6G-Session-3: Session 3: Digital Twin in 6G Session PerAI-6G-Session-4: Session 4: Resource Management in 6G Session PerAI-6G-Closing: Closing Session
Session WISARN-O: Opening Session WISARN-K1: Keynote Session WISARN-CB: Virtual Coffee Break Session WISARN-S1: Technical Session
Session Wireless-Sec-I: Wireless Security I Session Wireless-Sec-II: Wireless Security II

Session AidTSP-TS1

AidTSP Technical Session I

Conference
8:40 AM — 10:00 AM EDT
Local
May 20 Sat, 5:40 AM — 7:00 AM PDT

RansomCoin: A New Dataset for Analysing Cryptocurrency Transactions - Addressing a Gap in The Literature

Mohiuddin Ahmed; Clark Pagutaisidro; Apichart Alexander Pike; Yuting Yang; Al-Sakib Khan Pathan

0
This paper presents a ransomware payment transactions repository, RansomCoin and showcases the pattern analysis to understand the behaviour of ransomware attackers' money laundering tactics. Summarising data can help people make sense of it and improve data discovery, which can help search keyword queries. In this work, we created a bitcoin transaction dataset related to ransomware. Automation is designed and used with a specific algorithm to gather data from the blockchain and extract the data into a spreadsheet. The automation code also comes with a GUI (Graphical User Interface) with a user guide provided for everyone to use. The Ransomware Payment Transactions Dataset will help law enforcement trace the transaction and analyse the bitcoin movements in the blockchain. The Dataset has its suspicious/normal flag, which can help focus on the wallet address flagged as suspicious. Our analysis and obtained results allow us to understand blockchain better and how it functions.
Speaker Mohiuddin Ahmed (Edith Cowan University)

Dr. Mohiuddin Ahmed has been educating the next generation of cyber leaders and researching to disrupt the cybercrime ecosystem. His research is focused on ensuring national security and safeguarding critical infrastructures from cyber terrorists. Mohiuddin has edited several books and contributed articles to The Conversation. His research publications in reputed venues attracted more than 3200 citations and have been listed in the world's top 2% of scientists for the 2020-2022 citation impact. Mohiuddin secured several external and internal grants worth more than $1.5 Million and has been collaborating with academia and industry. He has been regularly invited to speak at international conferences and public organizations and interviewed by the media for expert opinion.

Scenario-Agnostic Zero-Trust Defense with Explainable Threshold Policy: A Meta-Learning Approach

Yunfei Ge; Tao Li; Quanyan Zhu

0
The increasing connectivity and intricate remote access environment have made traditional perimeter-based network defense vulnerable. Zero trust becomes a promising approach to provide defense policies based on agent-centric trust evaluation. However, the limited observations of the agent's trace bring information asymmetry in the decision-making. To facilitate the human understanding of the policy and the technology adoption, one needs to create a zero-trust defense that is explainable to humans and adaptable to different attack scenarios. To this end, we propose a scenario-agnostic zero-trust defense based on Partially Observable Markov Decision Processes (POMDP) and first-order Meta-Learning using only a handful of sample scenarios. The framework leads to an explainable and generalizable trust-threshold defense policy. To address the distribution shift between empirical security datasets and reality, we extend the model to a robust zero-trust defense minimizing the worst-case loss. We use case studies and real-world attacks to corroborate the results.
Speaker Yunfei Ge (New York University)

Yunfei Ge received B.S. degree in Honors in Optoelectronics from Sun Yat-Sen University, Guangzhou, China in 2017, and M.S degree in Electrical Engineering from Columbia University, New York, NY, USA, in 2019. She is currently pursuing Ph.D. degree in Electrical Engineering at New York University, New York, NY, USA. Her current research interests include game theory, multi-agent decision-making, cybersecurity, and cyber-physical systems.

Blockchain topology optimization based on node clustering

Peiyun Ran; Yipeng Ji; Mingsheng Liu; Peng Zhao; Shiyuan Yu; Yongjian Huang; Du Wang; Md Zakirul Alam Bhuiyan; Gang Li

0
Since blockchain was born more than ten years ago, its performance optimization has always been a hot topic in the academic community. Since blockchain is essentially a distributed system, it needs to set a consensus mechanism to enable nodes scattered around to reach consensus and tolerate a certain number of faulty nodes.In addition, for each block to be linked, it needs to be verified by all nodes and approved by more than half of the nodes before it can be truly linked. All these will add up to a large delay. As the number of nodes in the blockchain system increases, this delay will seriously reduce the efficiency of the system in processing transactions and reduce the scalability of the blockchain. Therefore, based on the goals of optimizing the blockchain system, increasing the transaction per second(TPS), and improving the scalability, this paper has improved the topology of the blockchain, and designed the corresponding consensus mechanism and message propagation mechanism.
Speaker Peiyun Ran

I'm a student study in School of Cyberspace Security of Beihang University.

Robust Federated Learning against Backdoor Attackers

Priyesh Ranjan; Ashish Gupta; Federico CorÚ; Sajal K. Das

0
Federated learning is a privacy-preserving alternative to regular edge learning that involves data transfer to the server. However, anonymous submission of gradients to the server can be used by adversaries to influence the model outcome, particularly through backdoor attacks where a trigger pattern is added to the data shard to manipulate the model outcomes on a specific sub-task. This work aims to identify such adversaries and isolate their weight updates to mitigate the effects of the attack. We propose two graph theoretic algorithms to identify the adversaries while maintaining data privacy. Under a classification task, our experimental results show that the proposed algorithms are superior to existing methods especially when numbers of attackers are more than the normal clients. Our algorithms are effective and robust to the attackers adding backdoor patterns at different location in the targeted images.
Speaker Priyesh Ranjan (University of Science and Technology Missouri)


Session Chair

Junggab Son (University of Nevada, USA)

Session AidTSP-TS2

AidTSP Technical Session II

Conference
10:30 AM — 12:00 PM EDT
Local
May 20 Sat, 7:30 AM — 9:00 AM PDT

Intrusion Detection System for IoHT Devices using Federated Learning

Fatemeh Mosaiyebzadeh; Seyedamin Pouriyeh; Reza M. Parizi; Meng Han; Daniel M. Batista

0
With the growing number of sensitive data transmitted in IT infrastructures, healthcare organizations and companies that generate users' wearable data have become a target for attackers. To protect electronic healthcare data, Internet of Healthcare Things (IoHT) devices must be protected by robust Intrusion Detection Systems (IDS) to provide a secure environment. Since it is undesirable to collect this data and perform machine learning tasks directly, recently, to preserve users' privacy, federated learning has obtained attention from the government and healthcare organizations. Unlike the centralized paradigm, federated learning is a privacy-aware machine learning framework designed to analyze data without sharing it. This paper proposes a deep neural network in federated learning (DNN-FL) to detect anomalies in the IoHT traffic that may result in security threats. We evaluate the detection performance of our proposal using metrics such as accuracy and precision. The proposed DNN-FL is validated using the wustl-ehms-2020 and ECU-IoHT datasets. It reached 91.40% of accuracy in detecting attacks in the first dataset and 98.47% in the second. All the developed source code in this work is being made publicly available to ensure reproducibility.
Speaker Fatemeh Mosaiyebzadeh (São Paulo University)

Fatemeh Mosaiyebzadeh received a Master's degree in Computer Science from the University of São Paulo, Brazil, in 2020. She is currently a Ph.D. student in Computer Science at the University of São Paulo, Brazil. Her current Ph.D. research focuses on the improvement of Intrusion Detection Systems (IDSs) in the Internet of Healthcare Things (IoHT) devices with Deep Learning and Federated Learning techniques.

Towards Trust Driven On-Demand Client Deployment in Federated Learning

Mario Bassam Chahoud; Azzam Mourad; Hadi Otrok; Mohsen Guizani

0
Federated Learning (FL) systems choose a certain number of clients from each round to take part in the learning. The ability to have more available clients in the learning areas is achieved using containerization technology. However, reliability concerns raise doubts about the trustworthiness of these devices as Docker containers are deployed on them to be able to serve as clients in FL scenarios. Moreover, the default random selection does not take into consideration trust values when selecting clients. Clients who are malicious may poison the learning process or the entire model if they are selected. In order to overcome these issues, we propose in this work that a trust factor must be considered while selecting these clients and deploying models in our architecture. We build a trust framework between the server and its available clients. The trust factor is continuously monitored and updated by checking clients that are not serving successfully the deployed jobs. In addition, it concludes relevant information about the local accuracy changes of each client by applying a two-step verification method to detect any label flipping and random updated weights.
The simulations utilize the mobile data challenge dataset. In each round, clients with high trustworthiness are selected. The simulations are compared with the default random selection method, and the centralized model. The suggested architecture is able to detect these clients while decreasing the number of normal and discarded rounds by assigning trust values to each client, updating this factor, and crediting malicious clients with a low trust factor.
Speaker mario chahoud (Mohamad Bin Zayed University of Artificial Intelligence, United Arab Emirates)

Mario Chahoud received his M.Sc. degree and B.S. degree in Computer Science from the Lebanese American University (LAU) in 2022 and 2020 respectively. He is currently a Research Fellow at the LAU Cyber Security Systems and Applied Artificial Intelligence Research Center and at Mohamad Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates. He was a Research and Teaching Assistant at the Lebanese American University. His current research interests include fog and cloud computing, Artificial intelligence, Machine learning, Federated Learning, and Cyber Security.

Anonymous Authentication Scheme for Federated Learning

Tianqi Zhou; Jian Shen; P Vijayakumar; Md Zakirul Alam Bhuiyan; S Audithan

0
As a distributed machine learning model, federated learning ensures the legitimate use of data and user privacy while training the global model. Existing privacy protection mechanisms for federated learning either need to balance training accuracy and privacy protection requirements, or lack of design from the perspective of groups. In this paper, we design a privacy protection mechanism from the perspective of groups for federated learning. By resorting to cryptographic techniques, the proposed mechanism is free of the tradeoff between accuracy and privacy. In particular, we aim to develop novel approaches for the asymmetric group key agreement (AGKA) protocol with efficient operations and lower storage cost, as well as to further support anonymous group authentication. First, we propose a BLS-AGKA protocol by using the Boneh-Lynn-Shacham (BLS) signature, which is computationally efficient and requires a relatively small storage cost. Second, to further achieve the privacy-preserving demand in federated learning, we construct an anonymous authentication scheme based on the proposed BLS-AGKA protocol, which supports anonymous group authentication. Finally, it is shown that the proposed protocol and scheme guarantee the desired security properties, including session-key security, unforgeability, and anonymity. In addition, the performance of the proposed scheme is superior to relevant existing works as well.
Speaker Tianqi Zhou (Zhejiang Sci-Tech University)

Tianqi Zhou received her B.S. and M.S. from the Nanjing University of Information Science and Technology, Nanjing, China in 2016 and 2019, respectively. She is currently working toward the Ph.D. degree in the School of Computer and Software, Nanjing University of Information Science and Technology. Also, she is currently a visiting Ph.D. student at Kyushu University, which is supported by the China Scholarship Council under Grant No. 202109040028. Her research interests include computer and network security, security systems, and cryptography.

Privacy Preservation in Kubernetes-based Federated Learning: A Networking Approach

Juan M. Parra; Luis Felix Gonzalez Blazquez; Anderson Bravalheri; Rasheed Hussain; Xenofon Vasilakos; Ivan Vidal; Francisco Valera; Reza Nejabati; Dimitra Simeonidou

0
Federated Learning (FL) is a distributed Machine Learning paradigm that enables multiple clients to collaboratively train a model under the control of a central server while preserving data locally in heterogeneous edge devices. Cloud computing and container-based approaches such as Kubernetes (K8s) have been recently proposed to facilitate scalable deployment of FL systems. K8s enables container orchestration for cloud and edge applications while reducing workload management complexity in FL ecosystems.
Nonetheless, K8s can violate fundamental FL privacy principles, e.g., the inherent flat networking approach in K8s can potentially allow FL clients to access other client or domain resources. The latter poses an open research problem and gap in the literature because serious privacy risks can arise from attackers gaining access to any client in the FL setup.
To address this problem, this paper presents a \emph{networking} approach via \emph{network isolation} at the link layer level, and \emph{authentication} and \emph{data packet encryption} at the network layer level. The former allows the creation of secure resource sharing, and the latter is used to protect in-transit data. For this purpose, we use a K8s networking operator and a secure network protocol suite.
The above combination facilitates on-demand link-layer connectivity, per-link data source authentication, and confidentiality between FL actors. We tested our approach on a network testbed composed of different geo-located nodes where FL clients are deployed. Our promising results showcase the feasibility of the approach for privacy preservation at the network level in K8s-based FL.
Speaker Juan Marcelo Parra


Session Chair

Changqing Luo (Virginia Commonwealth University, USA)

Session AidTSP-TS3

AidTSP Technical Session III

Conference
2:00 PM — 3:30 PM EDT
Local
May 20 Sat, 11:00 AM — 12:30 PM PDT

FeDiSa: A Semi-asynchronous Federated Learning Framework for Power System Fault and Cyberattack Discrimination

Muhammad Akbar Husnoo; Adnan Anwar; Haftu Tasew Reda; Nasser Hosseinzadeh; Shama N. Islam; Abdun Mahmood; Robin Doss

0
With growing security and privacy concerns in the Smart Grid (SG) domain, intrusion detection on critical energy infrastructure is an urgent priority that has garnered significant attention in recent years. To remedy the challenges of privacy preservation and decentralized power zones with strategic data owners, Federated Learning (FL) has contemporarily surfaced as a viable privacy-preserving alternative which enables collab- orative training of attack detection models without requiring the sharing of raw data. To address some of the technical challenges associated with conventional synchronous FL, this paper proposes FeDiSa, a novel Semi-asynchronous Federated learning framework for power system faults and cyberattack Discrimination which takes into account communication latency and stragglers. Specifically, we propose a collaborative training of deep auto-encoder by Supervisory Control and Data Acquisition (SCADA) sub-systems which upload their local model updates to a control centre, which then performs a semi-asynchronous model aggregation for a new global model parameters based on a buffer system and a preset cut-off time. Experiments on the proposed framework using publicly available Industrial Control Systems datasets reveal superior attack detection accuracy whilst preserving data confidentiality and minimizing the adverse effects of communication latency and stragglers. Furthermore, we see a 35% improvement in training time, thus validating the robustness of our proposed method.
Speaker Muhammad Akbar Husnoo

Muhammad Akbar Husnoo is currently a Ph.D. scholar at Deakin University. He received his dual B.Sc. (Hons) in Software Engineering from both Staffordshire University, UK and Asia Pacific University of Technology & Innovation, Malaysia in 2019. He also recently completed a Master of Data Science at Deakin University, Burwood, VIC, Australia in 2021. He has participated in several hackathons and is the ’Champion Winner’ of the SAS Malaysia FinTech Competition 2017–2018. Furthermore, he has been awarded ’The University Prize for Best Project of the B.Sc. (Hons) in Software Engineering Award 2018/2019’ for his honors thesis. Moreover, he was awarded the Deakin International Meritorious Scholarship for his masters degree, the CSRI 2020 Summer Scholarship and a full Deakin University Postgraduate Research Scholarship to pursue his doctorate. His research interests include privacy preservation, adversarial learning, deep learning, machine learning and other related topics.

Trustworthy and Load-Balancing Routing Scheme for Satellite Services with Multi-Agent DRL

Jiaxin Song; Ying Ju; Lei Liu; Qingqi Pei; Celimuge Wu; Mian Ahmad Jan; Shahid Mumtaz

0
Massive computing tasks of various applications have been generated in 6G space-air-ground integrated networks, and need to be transmitted securely and reliably. Nevertheless, the mobility of satellites and the untrusted nodes bring new challenges to the routing scheme design in low earth orbit (LEO) satellite networks. To improve the system trust and elevate the service quality, this paper proposes a fully distributed trustworthy load-balancing routing scheme for satellite services with a multi-agent dueling double deep Q network (D3QN)-based learning algorithm. Our scheme organizes multiple agents to generate hop-by-hop routes and makes decisions based on the trust value of the nodes, which has good scalability to deploy on various satellite constellations and can meet the trust requirements of the services. Besides, we add a variable delay constraint into the load minimization objective to meet various delay-sensitive satellite quality of service (QoS) requirements. We demonstrate that the proposed scheme dramatically reduces the link queue utilization rate and enhances the system capability of handling delay-sensitive services. The packet loss rate of our scheme is 24% lower than that of the benchmark scheme when the system has 30% malicious nodes.
Speaker Jiaxin Song

Jiaxin Song received a B.S. degree in Electronic information engineering from Nanjing University of Science and Technology, Nanjing, China, in 2020. He is working toward an M.S. in Information and Communication Engineering at the School of Communication Engineering, Xidian University, Xi'an, China. His research interests include satellite communication, routing, and deep reinforcement learning.

Avoid attacks: A Federated Data Sanitization Defense in IoMT Systems

Chong Chen; Ying Gao; Siquan Huang; Xingfu Yan

0
Malicious falsification of medical data destroys the training process of the medical-aided diagnosis models and causes serious damage to Healthcare IoMT Systems.
To solve this unsupervised problem, this paper finds a robust data filtering method for various data poisoning attacks.
First, we adapt the federated learning framework to project all of the clients' data features into the public subspace domain, allowing unified feature mapping to be established while their data remains stored locally.
Then we adopt the federated clustering to re-group their features to clarify the poisoned data.
The federated clustering is based on the consistent association of data and its semantics.
Finally, we do the data sanitization with a simple yet efficient strategy.
Extensive experiments are conducted to evaluate the accuracy and efficacy of the proposed defense method against data poisoning attacks.
Speaker Chong Chen(South China University of Technology)


Achieving Certified Robustness for Brain-Inspired Low-Dimensional Computing Classifiers

Fangfang Yang; Shijin Duan; Xiaolin Xu; Shaolei Ren

0
Brain-inspired hyperdimensional computing (HDC) in machine learning applications has been achieving great success in terms of energy efficiency and low latency. The proposal of low-dimensional computing (LDC) classification model not only improves the inference accuracy of existing HDC-based models
but also gets rid of the ultra-high dimension in them. However, the security part of LDC model to adversarial perturbations has not been touched. In this paper, we adopt the bounding technique, interval bound propagation (IBP), to train a LDC classification model that is provably robust against L? normbounded adversarial attacks. Specifically, we propagate the L? norm-bounded bounding box around the original input through layers of LDC model using interval arithmetic. After propagation,
the worst case prediction logits can be computed based on the upper bound and the lower bound of the output bounding box. By minimizing the loss between the worst case prediction and the true label, the predicted label could be kept invariant over all possible adversarial perturbations within L? norm-bounded ball. We evaluate the algorithm on both MNIST and fashion MNIST datasets. The experiment results corroborate that our trained models with IBP exhibit immunity and robustness against strong project gradient descent (PGD) attacking scheme and memory errors.
Speaker Fangfang Yang (University of California, Riverside)


Session Chair

Md Arafatur Rahman (University of Wolverhampton, UK)

Session AidTSP-TS4

AidTSP Technical Session IV

Conference
4:40 PM — 6:00 PM EDT
Local
May 20 Sat, 1:40 PM — 3:00 PM PDT

GPS Spoofing on UAV: A Survey

Ryan D Restivo; Laurel C. Dodson; Jian Wang; Wenkai Tan; Yongxin Liu; Huihui H Wang; Houbing H Song

0
With the development of the Internet of Things (IoT) and Cyber-Physical System (CPS), Unmanned Aerial Vehicles (UAVs) are deployed in various implementations which improve the performance of the IoT and reduce labor consumption significantly. As the core of UAV, Global Positioning System (GPS) is essential to provide the navigation information for UAVs to finish missions. GPS receives satellite signals and calculated localization so UAVs can recognize their positions. However, malicious attackers leverage the mechanism to generate forged GPS signals that can spoof UAV that has wrong positions. The wrong positions can lead to missions' failure and threaten public safety and private security. In this paper, we investigated the overview of GPS spoofing and explored the development of GPS spoofing on UAVs. This work can provide researchers with state-of-the-art GPS spoofing development on UAVs and inspiration for new directions in this field.
Speaker Houbing Song (University of Maryland, Baltimore County)

Houbing Song (M’12–SM’14-F’23) received the Ph.D. degree in electrical engineering from the University of Virginia, Charlottesville, VA, in August 2012.


He is currently a Tenured Associate Professor, the Director of the NSF Center for Aviation Big Data Analytics (Planning), the Associate Director for Leadership of the DOT Transportation Cybersecurity Center for Advanced Research and Education (Tier 1 Center), and the Director of the Security and Optimization for Networked Globe Laboratory (SONG Lab, www.SONGLab.us), University of Maryland, Baltimore County (UMBC), Baltimore, MD. Prior to joining UMBC, he was a Tenured Associate Professor of Electrical Engineering and Computer Science at Embry-Riddle Aeronautical University, Daytona Beach, FL. He serves as an Associate Editor for IEEE Transactions on Artificial Intelligence (TAI) (2023-present), IEEE Internet of Things Journal (2020-present), IEEE Transactions on Intelligent Transportation Systems (2021-present), and IEEE Journal on Miniaturization for Air and Space Systems (J-MASS) (2020-present). He was an Associate Technical Editor for IEEE Communications Magazine (2017-2020). He is the editor of eight books, the author of more than 100 articles and the inventor of 2 patents. His research interests include cyber-physical systems/internet of things, cybersecurity and privacy, and AI/machine learning/big data analytics. His research has been sponsored by federal agencies (including National Science Foundation, US Department of Transportation, and Federal Aviation Administration, among others) and industry. His research has been featured by popular news media outlets, including IEEE GlobalSpec's Engineering360, Association for Uncrewed Vehicle Systems International (AUVSI), Security Magazine, CXOTech Magazine, Fox News, U.S. News & World Report, The Washington Times, and New Atlas.


Dr. Song is an IEEE Fellow (for contributions to big data analytics and integration of AI with Internet of Things), and an ACM Distinguished Member (for outstanding scientific contributions to computing). He is an ACM Distinguished Speaker (2020-present) and an IEEE Vehicular Technology Society (VTS) Distinguished Lecturer (2023-present). Dr. Song has been a Highly Cited Researcher identified by Clarivate™ (2021, 2022) and a Top 1000 Computer Scientist identified by Research.com. He received Research.com Rising Star of Science Award in 2022 (World Ranking: 82; US Ranking: 16). In addition to 2021 Harry Rowe Mimno Award, Dr. Song was a recipient of 10+ Best Paper Awards from major international conferences, including IEEE CPSCom-2019, IEEE ICII 2019, IEEE/AIAA ICNS 2019, IEEE CBDCom 2020, WASA 2020, AIAA/ IEEE DASC 2021, IEEE GLOBECOM 2021 and IEEE INFOCOM 2022.

A Scalable Asynchronous Federated Learning for Privacy-Preserving Real-Time Surveillance Systems

Desta Haileselassie Hagos; Earl Tankard Jr.; Danda B. Rawat

0
A rise in popularity of decentralized Machine Learning (ML) algorithms, attributed to ensuring the privacy and security of users, has seen them being increasingly applied within the domain of healthcare, civilian and military mission-critical applications. Federated Learning (FL) is a promising privacy-preserving approach to distributed ML paradigm that enables collaboratively training a single high-quality intelligent model on a large corpus of decentralized data without sharing the local data with the central server. Most current state-of-the-art approaches to FL are based on synchronous communication strategies. Synchronous FL systems are communication efficient but have slow learning convergence due to stranglers and high energy costs. Furthermore, synchronous FL approaches have significant drawbacks in terms of scalability and efficiency as the size and complexity of the underlying system scale up, given the heterogeneity of participating devices. In this paper, we are expanding beyond the current state-of-the-art FL approaches by experimentally exploring the use of scalable asynchronous FL for privacy-preserving real-time surveillance systems.
Speaker Earl Tankard, Jr.


A Two-Tier Anomaly-based Intrusion Detection Approach for IoT-Enabled Smart Cities

Mosab Hamdan; Arwa Mohamed Eldhai; Samah Abdelsalam Abdalla; Kifayat Ullah; Ali Kashif Bashir; Muhammad Nadzir Bin Marsono; Fabio Kon; Daniel M. Batista

0
The Internet of Things (IoT), like other network infrastructures, requires Intrusion Detection Systems (IDSs) to be protected against attacks. When deploying an IDS in IoT-based smart city environments, the balance between latency and node capacity must be considered, which justifies a distributed IDS with specific classifiers based on the location of the system processing nodes. This paper proposes a two-level classification technique for collaborative anomaly-based IDSs deployed on fog and edge nodes. A Gradient Boosting Classifier (GBC) is used in the lower layer classifier at the edge, while a Convolutional Neural Network (CNN) is used in the upper layer classifier at the fog. Experimentation has demonstrated that the suggested IDS architecture outperforms previous solutions. For instance, in some scenarios, when comparing our proposal with Random Forest, the former obtained an accuracy equal to 99.1%, while the latter obtained 95.3%. Furthermore, our proposal can better select the most important network traffic features, reducing 76% of the data to be analyzed and improving privacy.
Speaker Mosab Hamdan (University of São Paulo)

Mosab Hamdan received a B.Sc. degree in Computer and Electronic System Engineering from the University of Science and Technology (UST), Sudan, in 2010, an M.Sc. degree in Computer Architecture and Networking from the University of Khartoum (UofK), Sudan, in 2014, and the Ph.D. degree in Electrical Engineering (Computer Networks) from the Faculty of Engineering, School of Electrical Engineering, Universiti Teknologi Malaysia (UTM), Malaysia, in 2021. From 2010 to 2015, he was a teaching assistant and lecturer with the Department of Computer and Electronics System Engineering, Faculty of Engineering, University of Science and Technology (UST). From July 2021 to January 2022, he was a Researcher with the Universiti Teknologi Malaysia under the Post-Doctoral Fellowship Scheme. He is currently working as a post-doctoral research fellow at the Institute of Mathematics and Statistics, University of São Paulo (USP). His current research interests are Computer Networks, Network Security, Software-Defined Networking (SDN), Internet-of-things (IoT), Smart Cities, and Future Networks.

Infrastructure Security Intrusion Detection with UAV and Wi-Fi Integrated IoT Networks

Fang Qi; Yingkai Zhao; Shaobo Zhang; Zhe Tang

0
This paper presents an intrusion detection method based on Wi-Fi signals acquired by IoT Networks and a UAV. We take the first step into the problem of physical security monitoring using the UAV with existing 5G and Wi-Fi infrastructure that does not need additional network deployment. The monitoring is conducted by an edge computing-assisted digital twin (EDT) deployed with the edge server. Therefore, we propose an EDT-driven 3-layer monitoring architecture for intrusion detection and monitoring around critical infrastructure perimeters. IoT devices use Wi-Fi signals through artificial intelligence techniques to process the signals and make a decision on the event and forward the decision to the EDT. We aim to minimize deployment and operational costs with respect to high-quality detection, time, and resources while increasing real-time intrusion detection and monitoring to provide a resilient, the trustworthy solution to physical infrastructure security. The preliminary performance analysis shows trustworthy monitoring performance regarding real-timelessness and accuracy.
Speaker Yingkai Zhao(Central South University)

He is a doctoral candidate at Central South University. His research interests include Internet of Things, network security, wireless sensing, etc.

Session Chair

Zakirul Alam Bhuiyan (Fordham University, USA)


Gold Sponsor


Gold Sponsor


Bronze Sponsor


Student Travel Grants


Student Travel Grants


Local Organizer

Made with in Toronto · Privacy Policy · INFOCOM 2020 · INFOCOM 2021 · INFOCOM 2022 · © 2023 Duetone Corp.