Sripath Mishra

Sripath Mishra

CS PhD candidate at Purdue. Anomaly and intrusion detection for edge and distributed systems — explainable AI, low-latency inference, federated learning, retrieval, GNNs. Seeking Applied Scientist / ML Engineer roles, 2027 start.

Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

UAV-CAS

A calibrated digital-twin dataset and benchmark for intrusion detection in UAV swarm networks — 99,492 flows across 1,024 configurations, calibrated against the NSF AERPAW testbed.

Posts

portfolio

FlowRAG — Two-Stage Edge–Cloud Intrusion Detection

An on-device fast path clears ~90% of flows in 4.78 ms (P99 6.16 ms) on a Raspberry Pi 4B; only ambiguous flows escalate to retrieval at the base station. +16% F1 over the strongest baseline under mobility-induced drift. IEEE EDGE 2026.

Interpretable Collaborative-Attack Detection

Recovering the set of attacks in a coordinated campaign from scenario-level labels — 0.88 set-precision — with decision rules auto-extracted from a surrogate tree and mapped to concrete operator mitigations. Under submission.

Trace Enrichment & Controlled Traffic Generation

A testbed isolating one network factor at a time, used to show that trace augmentation is method-specific — the same augmentation that helps size-sequence classifiers hurts timestamp-based ones. IEEE IPCCC 2025.

NetEye — Near-Switch Network Telemetry

Breaking the accuracy–scalability tradeoff in hybrid telemetry by replaying a near-switch window through every query, with FPGA compression to make replay affordable.

publications

A Real-Time Feature Indexing System on Live Video Streams

Published in 2020 IEEE 44th Annual Computer Software and Applications Conference (COMPSAC), 2020

This paper presents a real-time feature indexing system for live video streams.

Recommended citation: Aditya Chakraborty, Akshay Pawar, Hojoung Jang, Shunqiao Huang, Sripath Mishra, Shuo-Han Chen, Yuan-Hao Chang, George K. Thiruvathukal and Yung-Hsiang Lu. "A Real-Time Feature Indexing System on Live Video Streams." 2020 IEEE 44th Annual Computer Software and Applications Conference (COMPSAC), Madrid, Spain, 2020.
Download Paper

Automated Discovery of Network Cameras in Heterogeneous Web Pages

Published in ACM Transactions on Internet Technology, 22(1), Article 15, 2021

A general, automated system for aggregating network camera data spread across thousands of uniquely structured web pages — 57,364 cameras extracted from 237,257 pages.

Recommended citation: Ryan Dailey, Aniesh Chawla, Andrew Liu, Sripath Mishra, Ling Zhang, Josh Majors, Yung-Hsiang Lu, George K. Thiruvathukal. "Automated Discovery of Network Cameras in Heterogeneous Web Pages." ACM Transactions on Internet Technology, 22(1), Article 15, 2021, pp. 1–25.
Download Paper

Enriching Network Traffic Traces for Increasing Classification Accuracy

Published in IEEE International Performance, Computing, and Communications Conference (IPCCC), 2025

A testbed isolating one network factor at a time shows that trace augmentation is method-specific: the same augmentation that helps packet-size-sequence classifiers degrades timestamp-based ones.

Recommended citation: Sripath Mishra, Akhil Prasad, Sonia Fahmy. "Enriching Network Traffic Traces for Increasing Classification Accuracy." IEEE International Performance, Computing, and Communications Conference (IPCCC), Austin, TX, November 2025.
Download Paper

UAV-CAS: A Calibrated Digital-Twin Dataset for Intrusion Detection in UAV Swarm Networks

Published in arXiv:2606.17845 (dataset on IEEE DataPort), 2026

99,492 flows across 1,024 configurations from a Containernet digital twin calibrated against the NSF AERPAW testbed to 0.33 Hellinger divergence. Benchmarking 10 IDS shows binary detection saturating above 0.98 while stealth-paired collaborative attacks collapse to 0.51–0.86 AUROC.

Recommended citation: Sripath Mishra, Bharat Bhargava, Zizheng Liu, Shafkat Islam. "UAV-CAS: A Calibrated Digital-Twin Dataset for Intrusion Detection in UAV Swarm Networks." arXiv:2606.17845, 2026. Dataset: IEEE DataPort, doi:10.21227/zgrg-z865.
Download Paper

FlowRAG: A Two-Stage Retrieval-Augmented Intrusion Detection System for Adaptive UAV Network Security

Published in IEEE International Conference on Edge Computing and Communications (EDGE), 2026

A two-stage edge–cloud intrusion detector: an on-device fast path clears ~90% of flows in 4.78 ms (P99 6.16 ms) on a Raspberry Pi 4B, escalating only ambiguous flows to retrieval at the base station — +16% F1 over the strongest baseline under mobility-induced drift.

Recommended citation: Sripath Mishra, Shradha Awasthi, Bharat Bhargava, Zizheng Liu, Shafkat Islam. "FlowRAG: A Two-Stage Retrieval-Augmented Intrusion Detection System for Adaptive UAV Network Security." IEEE International Conference on Edge Computing and Communications (EDGE), 2026.

talks

teaching

Graduate Teaching Assistant - CS180

Undergraduate course, Purdue University, Computer Science Department, 2022

Guide undergraduate lab students in applying Object-Oriented Programming concepts in Java through hands-on exercises and evaluate their work.

Head Graduate Teaching Assistant - CS407

Undergraduate course, Purdue University, Computer Science Department, 2022

Help, supervise, and grade assignments and documents of students participating in an Agile environment to develop a group project.