About me
I am an Assistant Professor in Computer Science at UC Santa Barbara, and Faculty Affiliate at Lawrence Berkeley National Lab (LBNL) I co-direct the Systems and Networking Lab (SNL).
At SNL, I have been channeling my system-building skills toward addressing a range of pressing digital inequity challenges. Specifically, my research focuses on democratizing the development of production-ready ML artifacts for cybersecurity and enabling data-driven policymaking.
Prospective Students
Join us in shaping a more equitable digital world! If you are interested in building systems for a more inclusive digital future, come work with us. Please find more details about my research here.
Selected Publications
- In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems, ACM CCS, 2023.
- Decoding the Divide: Analyzing Disparities in Broadband Plans Offered by Major US ISPs, ACM SIGCOMM, 2023.
- AI/ML for Network Security: The Emperor has no Clothes, ACM CCS, 2022.
π Best Paper Honorable Mention
π IETF/IRTF Applied Networking Prize (ANRP) - The Importance of Contextualization of Crowdsourced Active Speed Test Measurements ACM IMC, 2022.
π Distinguished Paper Award (Long) - Detecting Ephemeral Optical Events with OpTel, USENIX NSDI, 2022.
Deployed at Tencent - An Effort to Democratize Networking Research in the Era of AI/ML, ACM HotNets 2019.
- Flexible and Scalable Systems for Network Management, Dissertation, Princeton University, 2018.
π ACM Doctoral Dissertation Award Honorable Mention - Sonata: Query-Driven Streaming Network Telemetry, ACM SIGCOMM 2018.
- iSDX: An Industrial-Scale Software Defined Internet Exchange Point, USENIX NSDI 2016.
π USENIX NSDI Community Contribution Award
π USENIX Best of the Rest - SDX: A Software Defined Internet Exchange, ACM SIGCOMM 2014.
π Internet2 Innovation Award
Please check this page for an extended list of publications.
Ongoing Projects
- Trustee: A framework that cracks open decision-making for black-box ML models (for networks) using high-fidelity, low-complexity, and stable decision trees.
- BQT: A tool that queries broadband plan offerings from major ISPs in the US at street-level granularity.
- PINOT: A programmable data-collection infrastructure at UCSB to collect fine-grained (labeled) network data at scale.
- netUnicorn: A data-collection platform that simplifies collecting network data for different learning problems from diverse network environments.
- netFound: A foundation model for networking data that employs self-supervised learning techniques on abundant unlabeled network data, passively collected from production environment using PINOT for task-agnostic pre-training and smaller-scale labeled network data, actively collected using PINOT and netUnicorn for task-specific fine-tuning.
Service
As a junior researcher, it has been an absolute honor and privilege to get the opportunities to organize different workshops (and tutorials) on topics related to digital equity and self-driving networks.
- ACM SIGCOMM 2023 Tutorial: Closed-Loop ML (for Networks) Pipelines, Sep 2023
- Bridging the Divide: Answering Internet Policy Questions with Cutting-Edge Network Measurement Algorithms, Datasets, and Platforms, June 2023
- ACM SIGMETRICS Workshop on Measurements for Self-Driving Networks, 2023, June 2023
- NSF Workshop on Internet Frontiers & Opportunities, Nov 2021
- NSF Workshop on NextG Security, Oct 2020
- NSF Workshop on Measurements for Self-driving Networks, Apr 2019
News
Mar 2024
: Our paper, Leveraging Prefix Structure to Detect Volumetric DDoS Attack Signatures with Programmable Switches, got accepted at IEEE Symposium on Security and Privacy (S&P), 2024. Kudos to Chris Misa for all the hard work and perseverance. This is the first work that demonstrates how we can leverage the fractal (self-similar) nature of IP addresses to design a more effective DDoS defense system.Jan 2024
: Our paper, Query Planning for Robust and Scalable Hybrid Network Telemetry Systems, got accepted at CoNEXT, 2024. Kudos to Chaofan Shou, a prodigious UCSB graduate, for his super-heroic effort. This work builds upon Sonata, developing a novel query planning technique to effectively handle changes in traffic or query workloads. This is my first paper with an undergraduate student as the lead author.Aug 2023
: Our paper, In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems, got accepted at ACM CCSβ23. Kudos to Roman for developing such an impressive and useful system! Please find more information about the project here.June 2023
: Udit Paul received the Computer Science Outstanding Publication Award. πJune 2023
: Udit Paul received the Computer Science Outstanding Dissertation Award. πMay 2023
: Our paper, Decoding the Divide: Analyzing Disparities in Broadband Plans Offered by Major US ISPs, got accepted at SIGCOMMβ23. Kudos to Udit Paul for such an impressive work! Please find more information about our BQT tool here.Jan 2023
: Our paper, Panakos: Chasing the Tails for Multidimensional Data Streams, got accepted at VLDBβ23. Kudos to Fuheng Zhao and Punnal Ismail Khan for their hard work and perseverance!Jan 2023
: Our project, Trustee, received the Applied Networking Prize (ANRP) from IETF/IRTF. Kudos to Arthur Jacobs and Roman Beltiukov for yet another recognition for their awesome work! πNov 2022
: Our paper, AI/ML for Network Security: The Emperor has no Clothes, received the Best Paper Honorable Mention at ACM SIGSAC Conference on Computer and Communications Security (CCS), 2022. It was rated as the best paper in theMachine Learning and Security
track. Special congratulations to Roman Beltiukov and Arthur Jacobs! πNov 2022
: I had the privilege to visit Lawrence Berkeley National Lab (LBNL). Special thanks to Inder Monga for hosting me.Oct 2022
: I had the privilege to present the Trustee work at ETH Zurich. Special thanks to Laurent Vanbever for hosting me.Oct 2022
: Our paper, The Importance of Contextualization of Crowdsourced Active Speed Test Measurements received the Distinguished Paper Award (Long) at ACM SIGCOMM Internet Measurements Conference (IMC), 2022. Special congratulations to my student, Udit Paul! πJune 2022
: Sanjay Chandrasekaran received the Computer Science Outstanding Graduate Research Award. πJune 2022
: Rohan Bhatia received the Computer Science Outstanding Teaching Assistant Award. πJune 2022
: Chaofan Shuo received the prestigious Computer Science Outstanding Undergraduate Research Award. πApr 2022
: Congcong Miao (Tencent) will present our work on detecting ephemeral network events in optical transport network at NSDI 2022.Feb 2022
: I talked about our efforts to democratize networking research at Googleβs Networking Research Summit.Jan 2022
: Sanjay Chandrasekaran received M-Labβs Research Fellowship 2022. Sanjay will be using the programmable research infrastructure at UCSB to study the relationship between the quality of experience (QoE) for applications and various QoS metrics from the network. π