• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.711-714
• /
• 2024

In the dynamic landscape of modern machine learning, Federated Learning (FL) has emerged as a compelling paradigm designed to enhance privacy by enabling participants to collaboratively train models without sharing their private data. Specifically, Distillation-based Federated Learning, like Federated Learning with Model Distillation (FedMD), Federated Gradient Encryption and Model Sharing (FedGEMS), and Differentially Secure Federated Learning (DS-FL), has arisen as a novel approach aimed at addressing Non-IID data challenges by leveraging Federated Learning. These methods refine the standard FL framework by distilling insights from public dataset predictions, securing data transmissions through gradient encryption, and applying differential privacy to mask individual contributions. Despite these innovations, our survey identifies persistent vulnerabilities, particularly concerning the susceptibility to logit inversion attacks where malicious actors could reconstruct private data from shared public predictions. This exploration reveals that even advanced Distillation-based Federated Learning systems harbor significant privacy risks, challenging the prevailing assumptions about their security and underscoring the need for continued advancements in secure Federated Learning methodologies.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.264-267
• /
• 2022

Recently, federated learning (FL) has increased prominence as a viable approach for enhancing user privacy and data security by allowing collaborative multi-party model learning without exchanging sensitive data. Despite this, most present FL systems still depend on a centralized aggregator to generate a global model by gathering all submitted models from users, which could expose user privacy and the risk of various threats from malicious users. To solve these issues, we suggested a safe FL framework that employs differential privacy to counter membership inference attacks during the collaborative FL model training process and empowers blockchain to replace the centralized aggregator server.

• 인터넷정보학회논문지
• /
• 제24권6호
• /
• pp.1-11
• /
• 2023

Federated learning (FL) is a ground breaking machine learning paradigm that allow smultiple participants to collaboratively train models in a cloud environment, all while maintaining the privacy of their raw data. This approach is in valuable in applications involving sensitive or geographically distributed data. However, one of the challenges in FL is dealing with heterogeneous and non-independent and identically distributed (non-IID) data across participants, which can result in suboptimal model performance compared to traditionalmachine learning methods. To tackle this, we introduce FedGCD, a novel FL algorithm that employs Graph Neural Network (GNN)-based community detection to enhance model convergence in federated settings. In our experiments, FedGCD consistently outperformed existing FL algorithms in various scenarios: for instance, in a non-IID environment, it achieved an accuracy of 0.9113, a precision of 0.8798,and an F1-Score of 0.8972. In a semi-IID setting, it demonstrated the highest accuracy at 0.9315 and an impressive F1-Score of 0.9312. We also introduce a new metric, nonIIDness, to quantitatively measure the degree of data heterogeneity. Our results indicate that FedGCD not only addresses the challenges of data heterogeneity and non-IIDness but also sets new benchmarks for FL algorithms. The community detection approach adopted in FedGCD has broader implications, suggesting that it could be adapted for other distributed machine learning scenarios, thereby improving model performance and convergence across a range of applications.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.119-130
• /
• 2022

Crime is a common social problem that affects the quality of life. As the number of crimes increases, it is necessary to build a model to predict the number of crimes that may occur in a given period, identify the characteristics of a person who may commit a particular crime, and identify places where a particular crime may occur. Data privacy is the main challenge that organizations face when building this type of predictive models. Federated learning (FL) is a promising approach that overcomes data security and privacy challenges, as it enables organizations to build a machine learning model based on distributed datasets without sharing raw data or violating data privacy. In this paper, a federated long short- term memory (LSTM) model is proposed and compared with a traditional LSTM model. Proposed model is developed using TensorFlow Federated (TFF) and the Keras API to predict the number of crimes. The proposed model is applied on the Boston crime dataset. The proposed model's parameters are fine tuned to obtain minimum loss and maximum accuracy. The proposed federated LSTM model is compared with the traditional LSTM model and found that the federated LSTM model achieved lower loss, better accuracy, and higher training time than the traditional LSTM model.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1462-1477
• /
• 2024

With the evolving complexity of connected vehicle features, the volume and diversity of data generated during driving continue to escalate. Enabling data sharing among interconnected vehicles holds promise for improving users' driving experiences and alleviating traffic congestion. Yet, the unintentional disclosure of users' private information through data sharing poses a risk, potentially compromising the interests of vehicle users and, in certain cases, endangering driving safety. Federated learning (FL) is a newly emerged distributed machine learning paradigm, which is expected to play a prominent role for privacy-preserving learning in autonomous vehicles. While FL holds significant potential to enhance the architecture of the Internet of Vehicles (IoV), the dynamic mobility of vehicles poses a considerable challenge to integrating FL with vehicular networks. In this paper, a novel clustered FL framework is proposed which is efficient for reducing communication and protecting data privacy. By assessing the similarity among feature vectors, vehicles are categorized into distinct clusters. An optimal vehicle is elected as the cluster head, which enhances the efficiency of personalized data processing and model training while reducing communication overhead. Simultaneously, the Local Differential Privacy (LDP) mechanism is incorporated during local training to safeguard vehicle privacy. The simulation results obtained from the 20newsgroups dataset and the MNIST dataset validate the effectiveness of the proposed scheme, indicating that the proposed scheme can ensure data privacy effectively while reducing communication overhead.

• 정보보호학회논문지
• /
• 제34권1호
• /
• pp.143-156
• /
• 2024

연합 학습(FL)은 여러 공동 작업자 간에 분산된 모델 학습을 위한 강력한 방법론으로 부상해 데이터 공유의 필요성을 없애준다. FL은 데이터 프라이버시를 보호하는 기능으로 호평을 받고 있지만, 다양한 유형의 프라이버시 공격으로부터 자유롭지 않다. 대표적인 개인정보 보호 기술인 차분 프라이버시(DP)는 이러한 취약점에 대응하기 위해 널리 사용된다. 이 논문에서는 기존의 작업별 적응형 DP 메커니즘을 FL 환경에 적용해 성능을 평가한다. 포괄적인 분석을 통해 다양한 DP 메커니즘이 공유 글로벌 모델의 성능에 미치는 영향을 평가하며, 특히 다양한 데이터 배포 및 분할 스키마에 주의를 기울인다. 이를 통해, FL에서 개인정보 보호와 유용성 간의 복잡한 상호 작용에 대한 이해를 심화하고, 성능 저하 없이 데이터를 보호할 수 있는 검증된 방법론을 제공한다.

• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.1-13
• /
• 2023

연합학습이 현대 인공지능 연구에 큰 패러다임을 가지고 오면서 다양한 분야의 연구에서 연합학습을 접목시키기 위한 노력을 하고 있다. 하지만 연합학습 적용을 위한 연구자들은 자신의 상황과 목적에 맞는 연합학습 프레임워크와 벤치마크 툴을 선택해야 하는 문제에 직면한다. 본 연구는 실제 연합학습을 적용하는 연구자의 상황을 고려한 연합학습 프레임워크 및 벤치마크 툴의 선택 가이드라인 제시를 목표로 한다. 특히, 본 연구에서는 3가지의 주요한 기여점이 존재한다. 첫번째, 연합학습을 적용하는 연구자의 상황을 연합학습의 목표와 결합하여 일반화하고, 각 상황에 적합한 연합학습 프레임워크의 선택 가이드라인을 제안한다. 두번째, 연구자에게 연합학습 프레임워크를 각각의 특징과 성능비교를 통해 선택의 적합성을 보여준다. 마지막으로, 현존하는 연합학습 프레임워크의 한계와 실세계 연합학습 운영을 위한 방안, 특히 생명주기 관리에 대한 플랫폼의 구조에 대해 제안한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.140-142
• /
• 2023

Federated learning (FL) is a new paradigm in machine learning (ML) that enables multiple devices to collaboratively train a shared ML model without sharing their local data. FL is well-suited for applications where data is sensitive or difficult to transmit in large volumes, or where collaborative learning is required. The Internet of Underwater Things (IoUT) is a network of underwater devices that collect and exchange data. This data can be used for a variety of applications, such as monitoring water quality, detecting marine life, and tracking underwater vehicles. However, the harsh underwater environment makes it difficult to collect and transmit data in large volumes. FL can address these challenges by enabling devices to train a shared ML model without having to transmit their data to a central server. This can help to protect the privacy of the data and improve the efficiency of training. In this view, this paper provides a brief overview of Fed-IoUT, highlighting its various applications, challenges, and opportunities.

• 한국산업정보학회논문지
• /
• 제28권4호
• /
• pp.21-34
• /
• 2023

연합학습은 동기식 연합학습과 비동기식 연합학습으로 구분된다. 그 중에서 비동기식 연합학습은 동기식 연합학습 보다 시간적인 이득이 있으나 좋은 모델 성능을 얻기 위한 도전 과제가 남아있다. 특히 non-IID 학습 데이터셋에서 성능열화 방지, 적절한 클라이언트 선택 및 오래된 그래디언트 정보 관리는 모델 성능 개선에 있어 중요하다. 본 논문에서는 K-비동기식 연합학습을 다루고 있으며 non-IID 데이터셋을 통해 학습한다. 또한 기존 방식이 선택할 클라이언트 수에 있어서 정적인 K개를 사용한 것과 달리 동적으로 K 값을 조절하는 알고리즘을 제안하여 학습 시간을 줄일 수 있었다. 추가적으로, 오래된 그래디언트를 다루는 방식을 활용해 모델 성능 개선을 이루었음을 보여준다. 마지막으로 강한 모델 안정성을 얻기 위해 모델 성능을 평가하는 방식을 활용하였다. 실험 결과를 통해 전체 알고리즘을 활용했을 때 학습 시간 단축, 모델 정확도 향상, 모델 안정성 향상의 이득을 얻을 수 있음을 보여준다.