Research Outputs

Permanent URI for this communityhttps://hdl.handle.net/20.500.14288/2

Browse

Filters

2020 - 20244

Advanced Search

Filter by

Settings

Indexed at: search.filters.indexed.WoSSubject: search.filters.subject.Internet of things

Search Results

Now showing 1 - 4 of 4
  • Placeholder
    PublicationMetadata only
    Byzantines can also learn from history: fall of centered clipping in federated learning
    (IEEE-Inst Electrical Electronics Engineers Inc, 2024) Özfatura, Emre; Gündüz, Deniz; Department of Computer Engineering; Özfatura, Ahmet Kerem; Küpçü, Alptekin; Department of Computer Engineering; Koç Üniversitesi İş Bankası Enfeksiyon Hastalıkları Uygulama ve Araştırma Merkezi (EHAM) / Koç University İşbank Center for Infectious Diseases (KU-IS CID); Graduate School of Sciences and Engineering; College of Engineering;  
    The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks.
  • Placeholder
    PublicationMetadata only
    Data-agnostic model poisoning against federated learning: a graph autoencoder approach
    (IEEE-Inst Electrical Electronics Engineers Inc, 2024) Li, Kai; Zheng, Jingjing; Yuan, Xin; Ni, Wei; Poor, H. Vincent; Department of Electrical and Electronics Engineering; Akan, Özgür Barış; Department of Electrical and Electronics Engineering;  ; College of Engineering;  
    This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both effectiveness and undetectability. By listening to the benign local models and the global model, the attacker extracts the graph structural correlations among the benign local models and the training data features substantiating the models. The attacker then adversarially regenerates the graph structural correlations while maximizing the FL training loss, and subsequently generates malicious local models using the adversarial graph structure and the training data features of the benign ones. A new algorithm is designed to iteratively train the malicious local models using GAE and sub-gradient descent. The convergence of FL under attack is rigorously proved, with a considerably large optimality gap. Experiments show that the FL accuracy drops gradually under the proposed attack and existing defense mechanisms fail to detect it. The attack can give rise to an infection across all benign devices, making it a serious threat to FL. © 2005-2012 IEEE.
  • Placeholder
    PublicationMetadata only
    Flexible and cognitive radio access technologies for 5G and beyond
    (Institution of Engineering and Technology, 2020) Arslan, Hüseyin; Department of Electrical and Electronics Engineering; Başar, Ertuğrul; Faculty Member; Department of Electrical and Electronics Engineering; College of Engineering; 149116
    Standards for 5G and beyond will require communication systems with a much more flexible and cognitive design to support a wide variety of services including smart vehicles, smart cities, smart homes, IoTs, and remote health. Although future 6G technologies may look like an extension of their 5G counterparts, new user requirements, completely new applications and use-cases, and networking trends will bring more challenging communication engineering problems. New communication paradigms in different layers will be required, in particular in the physical layer of future wireless communication systems. This comprehensive book is intended to be both a tutorial on flexible and cognitive radio access technologies for 5G and beyond and an advanced overview for technical professionals and managers in the communications industry, as well as researchers in academia and industry. The authors cover enabling radio access technologies for 5G and beyond, not only from a standard specific angle (like 5G) but also by considering future trends beyond 5G. Rather than specific standard implementations, the book covers a wide variety of technologies and their uses. The presentations are both descriptive and mathematical in nature to cater to readers who need mathematical description as well as readers who do not. The book is written at a level suited to readers who already have a background in electrical engineering and basic wireless communications.
  • Placeholder
    PublicationMetadata only
    Intelligent edge computing: state-of-the-art techniques and applications
    (Institute of Electrical and Electronics Engineers Inc., 2020) Department of Computer Engineering; Department of Computer Engineering; N/A; Gürsoy, Attila; Özkasap, Öznur; Gill, Waris; Faculty Member; Faculty Member; PhD Student; Department of Computer Engineering; College of Engineering; College of Engineering; Graduate School of Sciences and Engineering; 8745; 113507; N/A
    To enable intelligent decisions at the network edge, supervised and unsupervised machine learning techniques and their variations are highly utilized in recent research studies. These include techniques and the corresponding applications such as detecting manufacturing faults in a smart factory setting, monitoring patient activities and health problems in smart health systems, detecting security attacks on the Internet of Things devices, and finding the rare events in the audio signals. In this paper, we present an extensive review of state-of-the-art techniques and applications of intelligent edge computing and provide classification and discussion of various approaches in this field.