Abstract:
The increasing success of Machine Learning (ML) and Deep Learning (DL) has recently re-sparked interest towards traffic classification. While supervised techniques provid...Show MoreMetadata
Abstract:
The increasing success of Machine Learning (ML) and Deep Learning (DL) has recently re-sparked interest towards traffic classification. While supervised techniques provide satisfactory performance when classifying known traffic, the detection of zero-day (i.e., unknown) traffic is a more challenging task. At the same time, zero-day detection, generally tackled with unsupervised techniques such as clustering, received less coverage by the traffic classification literature which focuses more on deriving DL models via supervised techniques. Moreover, the combination of supervised and unsupervised techniques poses challenges not fully covered by the traffic classification literature. In this paper, we share our experience on a commercial-grade DL traffic classification engine that combines supervised and unsupervised techniques to identify known and zero-day traffic. In particular, we rely on a dataset with hundreds of very fine grained application labels, and perform a thorough assessment of two state of the art traffic classifiers in commercial-grade settings. This pushes the boundaries of traffic classifiers evaluation beyond the few tens of classes typically used in the literature. Our main contribution is the design and evaluation of GradBP, a novel technique for zero-day applications detection. Based on gradient backpropagation and tailored for DL models, GradBP yields superior performance with respect to state of the art alternatives, in both accuracy and computational cost. Overall, while ML and DL models are both equally able to provide excellent performance for the classification of known traffic, the non-linear feature extraction process of DL models backbone provides sizable advantages for the detection of unknown classes over classical ML models.
Published in: IEEE Transactions on Network and Service Management ( Volume: 18, Issue: 4, December 2021)

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Lixuan Yang received the M.Sc. degree from Jean Monet University in 2013, and the Ph.D. degree from the CNAM in 2017. She is a Senior Engineer with the DataCom Lab, Huawei Technologies, France. She worked with the XXII Group as an Artificial Intelligence Team Leader on computer vision and natural language processing projects. Her current interests include traffic classification, federated learning, and continual learning.
Lixuan Yang received the M.Sc. degree from Jean Monet University in 2013, and the Ph.D. degree from the CNAM in 2017. She is a Senior Engineer with the DataCom Lab, Huawei Technologies, France. She worked with the XXII Group as an Artificial Intelligence Team Leader on computer vision and natural language processing projects. Her current interests include traffic classification, federated learning, and continual learning.View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Alessandro Finamore received the Ph.D. degree from the Politecnico di Torino in 2012. He is a Principal Engineer with the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2019, he was a Principal Engineer with Telefonica UK/O2, London, U.K., and an Associate Research with Telefonica Research, Barcelona, Spain. He has coauthored more than 80 papers in leading conferences and journals, including the Best P...Show More
Alessandro Finamore received the Ph.D. degree from the Politecnico di Torino in 2012. He is a Principal Engineer with the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2019, he was a Principal Engineer with Telefonica UK/O2, London, U.K., and an Associate Research with Telefonica Research, Barcelona, Spain. He has coauthored more than 80 papers in leading conferences and journals, including the Best P...View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Feng Jun is a Data Scientist and a AI Architect Expert with Huawei Data Communication Product Line. He has over 20 years of experience in data analysis and AI deployment in the telecommunications industry.
Feng Jun is a Data Scientist and a AI Architect Expert with Huawei Data Communication Product Line. He has over 20 years of experience in data analysis and AI deployment in the telecommunications industry.View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Dario Rossi (Senior Member, IEEE) is a Network AI CTO and the Director of the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2018, he held a Full Professor positions with Telecom Paris and École Polytechnique and was a holder of Cisco’s Chair NewNet Paris. He has coauthored 15 patents and over 200 papers in leading conferences and journals, that received nine best paper awards, a Google Faculty Researc...Show More
Dario Rossi (Senior Member, IEEE) is a Network AI CTO and the Director of the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2018, he held a Full Professor positions with Telecom Paris and École Polytechnique and was a holder of Cisco’s Chair NewNet Paris. He has coauthored 15 patents and over 200 papers in leading conferences and journals, that received nine best paper awards, a Google Faculty Researc...View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Lixuan Yang received the M.Sc. degree from Jean Monet University in 2013, and the Ph.D. degree from the CNAM in 2017. She is a Senior Engineer with the DataCom Lab, Huawei Technologies, France. She worked with the XXII Group as an Artificial Intelligence Team Leader on computer vision and natural language processing projects. Her current interests include traffic classification, federated learning, and continual learning.
Lixuan Yang received the M.Sc. degree from Jean Monet University in 2013, and the Ph.D. degree from the CNAM in 2017. She is a Senior Engineer with the DataCom Lab, Huawei Technologies, France. She worked with the XXII Group as an Artificial Intelligence Team Leader on computer vision and natural language processing projects. Her current interests include traffic classification, federated learning, and continual learning.View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Alessandro Finamore received the Ph.D. degree from the Politecnico di Torino in 2012. He is a Principal Engineer with the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2019, he was a Principal Engineer with Telefonica UK/O2, London, U.K., and an Associate Research with Telefonica Research, Barcelona, Spain. He has coauthored more than 80 papers in leading conferences and journals, including the Best Paper Award at CoNEXT.
Alessandro Finamore received the Ph.D. degree from the Politecnico di Torino in 2012. He is a Principal Engineer with the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2019, he was a Principal Engineer with Telefonica UK/O2, London, U.K., and an Associate Research with Telefonica Research, Barcelona, Spain. He has coauthored more than 80 papers in leading conferences and journals, including the Best Paper Award at CoNEXT.View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Feng Jun is a Data Scientist and a AI Architect Expert with Huawei Data Communication Product Line. He has over 20 years of experience in data analysis and AI deployment in the telecommunications industry.
Feng Jun is a Data Scientist and a AI Architect Expert with Huawei Data Communication Product Line. He has over 20 years of experience in data analysis and AI deployment in the telecommunications industry.View more

Data Communication Department, Huawei Technologies, Boulogne Billancourt, France
Dario Rossi (Senior Member, IEEE) is a Network AI CTO and the Director of the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2018, he held a Full Professor positions with Telecom Paris and École Polytechnique and was a holder of Cisco’s Chair NewNet Paris. He has coauthored 15 patents and over 200 papers in leading conferences and journals, that received nine best paper awards, a Google Faculty Research Award in 2015 and an IRTF Applied Network Research Prize in 2016. He is a Senior Member of ACM.
Dario Rossi (Senior Member, IEEE) is a Network AI CTO and the Director of the DataCom Lab, Huawei Technologies, France. Before joining Huawei in 2018, he held a Full Professor positions with Telecom Paris and École Polytechnique and was a holder of Cisco’s Chair NewNet Paris. He has coauthored 15 patents and over 200 papers in leading conferences and journals, that received nine best paper awards, a Google Faculty Research Award in 2015 and an IRTF Applied Network Research Prize in 2016. He is a Senior Member of ACM.View more