From the 1 of 6 linked papers with an AI index.
6 papers
Pramana: A Composable, Domain-Specific Backend for Empirical Networking Research
Jaber Daneshamooz, Eugene Vuong, Alagappan Ramanathan +11
The paper presents Pramana, a composable, domain‑specific backend that separates experiment intent from execution substrate to streamline the generation of empirical networking dat…
NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series
Satyandra Guthula, Jaber Daneshamooz, Charles Fleming +3
Network operators monitor their infrastructure by collecting telemetry data such as packet counts, byte rates, or flow volumes, yet answering the questions that effective operation…
NetForge: A Programmable Substrate for Bottleneck-Centric Network Data Generation
Jaber Daneshamooz, Satyandra Guthula, Jessica Nguyen +5
The behavior of Internet applications is shaped by congestion dynamics at bottleneck links, yet data capturing application behavior across diverse bottleneck regimes remains scarce…
Demystifying Network Foundation Models
Sylee Beltiukov, Satyandra Guthula, Wenbo Guo +2
This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs) that focuses on hidden representations analysis rather than…
SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Murayyiam Parvez, Annus Zulfiqar, Roman Beltiukov +4
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network…
The Multifractal IP Address Structure: Physical Explanation and Implications
Chris Misa, Ram Durairajan, Arpit Gupta +2
The structure of IP addresses observed in Internet traffic plays a critical role for a wide range of networking problems of current interest. For example, modern network telemetry…