P4Pir

Zang, Mingyuan; Zheng, Changgang; Stoyanov, Radostin; Dittmann, Lars; Zilberman, Noa

doi:10.1145/3546037.3546060

Cited by 7 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a single-switch deployment in previous work [5], it is assumed that collected traffic features are shared in digests to the control plane/server. In FLIP4, such data sharing step is avoided by introducing the FL method to share model parameters instead.…”

Section: Implementation a In-network Attack Detection And Model Mappingmentioning

confidence: 99%

“…Offloading attack detection services from the remote server/cloud to the network edge has been proposed as a means to provide prompt reaction [3,4]. The advent of programmable data planes and in-network ML inference have further driven possibilities for in-network attack detection [5]. Building upon programmable pipelines and P4 language, an ML inference process can be mapped to the data plane to directly make a detection decision along with packet forwarding.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning-Based In-Network Traffic Analysis on IoT Edge

Zang

Zheng

Koziak

et al. 2023

2023 IFIP Networking Conference (IFIP Networking)

Self Cite

View full text Add to dashboard Cite

The rise of IoT-connected devices has led to an increase in collected data for service and traffic analysis, but also to emerging threats and attacks. In-network machine learningbased attack detection has proven effective in fast response, but scaling to distributed IoT edge devices risks increasing communication overheads and raising data privacy concerns. To address these concerns, we present FLIP4, a distributed innetwork attack detection framework based on federated tree models. FLIP4 maintains data privacy by enabling distributed machine learning training while keeping data local on IoT edge, and provides in-network inference within the programmable data plane on edge gateway for timely attack labeling and mitigation. Evaluation results show that FLIP4 can accurately detect attacks while maintaining source data privacy and enabling lightweight deployment on IoT edge.

show abstract

Section: Implementation a In-network Attack Detection And Model Mappingmentioning

confidence: 99%