In-network machine learning using programmable network devices: A survey

C Zheng, X Hong, D Ding, S Vargaftik… - … Surveys & Tutorials, 2023 - ieeexplore.ieee.org
Machine learning is widely used to solve networking challenges, ranging from traffic
classification and anomaly detection to network configuration. However, machine learning …

Offloading machine learning to programmable data planes: A systematic survey

R Parizotto, BL Coelho, DC Nunes, I Haque… - ACM Computing …, 2023 - dl.acm.org
The demand for machine learning (ML) has increased significantly in recent decades,
enabling several applications, such as speech recognition, computer vision, and …

An efficient design of intelligent network data plane

G Zhou, Z Liu, C Fu, Q Li, K Xu - 32nd USENIX Security Symposium …, 2023 - usenix.org
Deploying machine learning models directly on the network data plane enables intelligent
traffic analysis at line-speed using data-driven models rather than predefined protocols …

{HorusEye}: A Realtime {IoT} Malicious Traffic Detection Framework using Programmable Switches

Y Dong, Q Li, K Wu, R Li, D Zhao, G Tyson… - 32nd USENIX Security …, 2023 - usenix.org
The ever-growing volume of IoT traffic brings challenges to IoT anomaly detection systems.
Existing anomaly detection systems perform all traffic detection on the control plane, which …

Flowrest: Practical flow-level inference in programmable switches with random forests

ATJ Akem, M Gucciardo, M Fiore - IEEE INFOCOM 2023-IEEE …, 2023 - ieeexplore.ieee.org
User-plane machine learning facilitates low-latency, high-throughput inference at line rate.
Yet, user planes are highly constrained environments, and restrictions are especially …

DDoS family: A novel perspective for massive types of DDoS attacks

Z Zhao, Z Li, Z Zhou, J Yu, Z Song, X **e, F Zhang… - Computers & …, 2024 - Elsevier
Abstract Distributed Denial of Service (DDoS) defense is a profound research problem. In
recent years, adversaries tend to complicate their attack strategies by crafting vast DDoS …

Towards continuous threat defense: In-network traffic analysis for IoT gateways

M Zang, C Zheng, L Dittmann… - IEEE Internet of Things …, 2023 - ieeexplore.ieee.org
The widespread use of IoT devices has unveiled overlooked security risks. With the advent
of ultrareliable low-latency communications (URLLCs) in 5G, fast threat defense is critical to …

pforest: In-network inference with random forests

C Busse-Grawitz, R Meier, A Dietmüller… - arxiv preprint arxiv …, 2019 - arxiv.org
When classifying network traffic, a key challenge is deciding when to perform the
classification, ie, after how many packets. Too early, and the decision basis is too thin to …

RIDS: Towards advanced ids via rnn model and programmable switches co-designed approaches

Z Zhao, Z Li, Z Song, F Zhang… - IEEE INFOCOM 2024 …, 2024 - ieeexplore.ieee.org
Existing Deep Learning (DL)-based network Intrusion Detection System (IDS) is able to
characterize sequence semantics of traffic and discover malicious behaviors. Yet DL models …

Leveraging prefix structure to detect volumetric ddos attack signatures with programmable switches

C Misa, R Durairajan, A Gupta… - … IEEE Symposium on …, 2024 - ieeexplore.ieee.org
As increasingly complex and dynamic volumetric DDoS attacks continue to wreak havoc on
edge networks, two recent developments promise to bolster DDoS defense at the edge …