FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning. Wang, N., Chen, Y., Hu, Y., Lou, W., & Hou, Y. T. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, pages 1409–1418, May, 2022. ISSN: 2641-9874![FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 1 download Over the last decade, Internet of Things (IoT) has permeated our daily life with a broad range of applications. However, a lack of sufficient security features in IoT devices renders IoT ecosystems vulnerable to various network intrusion attacks, potentially causing severe damage. Previous works have explored using machine learning to build anomaly detection models for defending against such attacks. In this paper, we propose FeCo, a federated-contrastive-learning framework that coordinates in-network IoT devices to jointly learn intrusion detection models. FeCo utilizes federated learning to alleviate users’ privacy concerns as participating devices only submit their model parameters rather than local data. Compared to previous works, we develop a novel representation learning method based on contrastive learning that is able to learn a more accurate model for the benign class. FeCo significantly improves the intrusion detection accuracy compared to previous works. Besides, we implement a two-step feature selection scheme to avoid overfitting and reduce computation time. Through extensive experiments on the NSL-KDD dataset, we demonstrate that FeCo achieves as high as 8% accuracy improvement compared to the state-of-the-art and is robust to non-IID data. Evaluations on convergence, computation overhead, and scalability further confirm the suitability of FeCo for IoT intrusion detection.
@inproceedings{wang_feco_2022,
title = {{FeCo}: {Boosting} {Intrusion} {Detection} {Capability} in {IoT} {Networks} via {Contrastive} {Learning}},
shorttitle = {{FeCo}},
url = {https://ieeexplore.ieee.org/abstract/document/9796926},
doi = {10.1109/INFOCOM48880.2022.9796926},
abstract = {Over the last decade, Internet of Things (IoT) has permeated our daily life with a broad range of applications. However, a lack of sufficient security features in IoT devices renders IoT ecosystems vulnerable to various network intrusion attacks, potentially causing severe damage. Previous works have explored using machine learning to build anomaly detection models for defending against such attacks. In this paper, we propose FeCo, a federated-contrastive-learning framework that coordinates in-network IoT devices to jointly learn intrusion detection models. FeCo utilizes federated learning to alleviate users’ privacy concerns as participating devices only submit their model parameters rather than local data. Compared to previous works, we develop a novel representation learning method based on contrastive learning that is able to learn a more accurate model for the benign class. FeCo significantly improves the intrusion detection accuracy compared to previous works. Besides, we implement a two-step feature selection scheme to avoid overfitting and reduce computation time. Through extensive experiments on the NSL-KDD dataset, we demonstrate that FeCo achieves as high as 8\% accuracy improvement compared to the state-of-the-art and is robust to non-IID data. Evaluations on convergence, computation overhead, and scalability further confirm the suitability of FeCo for IoT intrusion detection.},
urldate = {2024-02-08},
booktitle = {{IEEE} {INFOCOM} 2022 - {IEEE} {Conference} on {Computer} {Communications}},
author = {Wang, Ning and Chen, Yimin and Hu, Yang and Lou, Wenjing and Hou, Y. Thomas},
month = may,
year = {2022},
note = {ISSN: 2641-9874},
keywords = {Biological system modeling, Data privacy, Feature extraction, Intrusion detection, Representation learning, Scalability, Telecommunication traffic},
pages = {1409--1418},
}
Downloads: 1
{"_id":"ANp7zEi2SbwRh4vbq","bibbaseid":"wang-chen-hu-lou-hou-fecoboostingintrusiondetectioncapabilityiniotnetworksviacontrastivelearning-2022","author_short":["Wang, N.","Chen, Y.","Hu, Y.","Lou, W.","Hou, Y. T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning","shorttitle":"FeCo","url":"https://ieeexplore.ieee.org/abstract/document/9796926","doi":"10.1109/INFOCOM48880.2022.9796926","abstract":"Over the last decade, Internet of Things (IoT) has permeated our daily life with a broad range of applications. However, a lack of sufficient security features in IoT devices renders IoT ecosystems vulnerable to various network intrusion attacks, potentially causing severe damage. Previous works have explored using machine learning to build anomaly detection models for defending against such attacks. In this paper, we propose FeCo, a federated-contrastive-learning framework that coordinates in-network IoT devices to jointly learn intrusion detection models. FeCo utilizes federated learning to alleviate users’ privacy concerns as participating devices only submit their model parameters rather than local data. Compared to previous works, we develop a novel representation learning method based on contrastive learning that is able to learn a more accurate model for the benign class. FeCo significantly improves the intrusion detection accuracy compared to previous works. Besides, we implement a two-step feature selection scheme to avoid overfitting and reduce computation time. Through extensive experiments on the NSL-KDD dataset, we demonstrate that FeCo achieves as high as 8% accuracy improvement compared to the state-of-the-art and is robust to non-IID data. Evaluations on convergence, computation overhead, and scalability further confirm the suitability of FeCo for IoT intrusion detection.","urldate":"2024-02-08","booktitle":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Ning"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Yimin"],"suffixes":[]},{"propositions":[],"lastnames":["Hu"],"firstnames":["Yang"],"suffixes":[]},{"propositions":[],"lastnames":["Lou"],"firstnames":["Wenjing"],"suffixes":[]},{"propositions":[],"lastnames":["Hou"],"firstnames":["Y.","Thomas"],"suffixes":[]}],"month":"May","year":"2022","note":"ISSN: 2641-9874","keywords":"Biological system modeling, Data privacy, Feature extraction, Intrusion detection, Representation learning, Scalability, Telecommunication traffic","pages":"1409–1418","bibtex":"@inproceedings{wang_feco_2022,\n\ttitle = {{FeCo}: {Boosting} {Intrusion} {Detection} {Capability} in {IoT} {Networks} via {Contrastive} {Learning}},\n\tshorttitle = {{FeCo}},\n\turl = {https://ieeexplore.ieee.org/abstract/document/9796926},\n\tdoi = {10.1109/INFOCOM48880.2022.9796926},\n\tabstract = {Over the last decade, Internet of Things (IoT) has permeated our daily life with a broad range of applications. However, a lack of sufficient security features in IoT devices renders IoT ecosystems vulnerable to various network intrusion attacks, potentially causing severe damage. Previous works have explored using machine learning to build anomaly detection models for defending against such attacks. In this paper, we propose FeCo, a federated-contrastive-learning framework that coordinates in-network IoT devices to jointly learn intrusion detection models. FeCo utilizes federated learning to alleviate users’ privacy concerns as participating devices only submit their model parameters rather than local data. Compared to previous works, we develop a novel representation learning method based on contrastive learning that is able to learn a more accurate model for the benign class. FeCo significantly improves the intrusion detection accuracy compared to previous works. Besides, we implement a two-step feature selection scheme to avoid overfitting and reduce computation time. Through extensive experiments on the NSL-KDD dataset, we demonstrate that FeCo achieves as high as 8\\% accuracy improvement compared to the state-of-the-art and is robust to non-IID data. Evaluations on convergence, computation overhead, and scalability further confirm the suitability of FeCo for IoT intrusion detection.},\n\turldate = {2024-02-08},\n\tbooktitle = {{IEEE} {INFOCOM} 2022 - {IEEE} {Conference} on {Computer} {Communications}},\n\tauthor = {Wang, Ning and Chen, Yimin and Hu, Yang and Lou, Wenjing and Hou, Y. Thomas},\n\tmonth = may,\n\tyear = {2022},\n\tnote = {ISSN: 2641-9874},\n\tkeywords = {Biological system modeling, Data privacy, Feature extraction, Intrusion detection, Representation learning, Scalability, Telecommunication traffic},\n\tpages = {1409--1418},\n}\n\n","author_short":["Wang, N.","Chen, Y.","Hu, Y.","Lou, W.","Hou, Y. T."],"key":"wang_feco_2022","id":"wang_feco_2022","bibbaseid":"wang-chen-hu-lou-hou-fecoboostingintrusiondetectioncapabilityiniotnetworksviacontrastivelearning-2022","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/abstract/document/9796926"},"keyword":["Biological system modeling","Data privacy","Feature extraction","Intrusion detection","Representation learning","Scalability","Telecommunication traffic"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/8994433/collections/66SDI5S7/items?key=ozCmKMmrE26WwEN9PAdOLaiV&format=bibtex&limit=100","dataSources":["Rxy8umoNP78qdq56v","8BDe79PKmLEoGEieK","kQ6oEMED6p4RGbihm","yM68t35RzDgJZajbn","nXz2cN22CbQDukEnJ"],"keywords":["biological system modeling","data privacy","feature extraction","intrusion detection","representation learning","scalability","telecommunication traffic"],"search_terms":["feco","boosting","intrusion","detection","capability","iot","networks","via","contrastive","learning","wang","chen","hu","lou","hou"],"title":"FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning","year":2022,"downloads":1}