CV
Education
- Ph.D. in Computer Science, Purdue University, West Lafayette, IN — Jan 2022 – May 2027 (expected)
- Advisor: Prof. Bharat Bhargava
- M.S. in Computer Science, University of California, Los Angeles, CA — Dec 2021
- B.S. in Computer Science, Purdue University, West Lafayette, IN — May 2020
- Honors; Dean’s Honor List; Best Sophomore Award in Computer Science
Research Experience
Intrusion Detection for UAV Networks — Research Assistant, Prof. Bharat Bhargava’s group (Jan 2025 – Present)
- Engineered FlowRAG, an edge–cloud detector built on the finding that on-device latency, not accuracy, is the binding constraint for edge deployment: an on-device screen clears 90% of flows in 4.78 ms (P99 6.16 ms) on a Raspberry Pi 4B, escalating only ambiguous flows — +16% F1 over the strongest baseline under mobility drift (IEEE EDGE 2026).
- Redefined retrieval for detection: retrieval regenerates training sets instead of text, so the detector absorbs new attack variants without catastrophic forgetting — +7–10 F1 points over baselines (0.81–0.82 vs. 0.72–0.75) across 5–20-UAV swarms.
- Created UAV-CAS, a 99,492-flow digital-twin dataset calibrated against real AERPAW hardware to 0.33 Hellinger divergence. Benchmarking 10 IDS exposed a field-wide blind spot: binary detection saturates above 0.98 while stealth-paired collaborative attacks collapse to 0.51–0.86 AUROC (arXiv:2606.17845).
- Designed an interpretable two-level detector recovering collaborative attack sets from scenario-level labels: cross-flow synchrony and destination-convergence features reach 0.88 set-precision, with named-threshold rules explaining the flood classes at 0.94–0.99 F1, each mapped to an operator mitigation. 10-packet prefixes land within 2 points of full-flow accuracy (under submission).
Robust Traffic Classification Under Distribution Shift — Research Assistant, Prof. Sonia Fahmy’s group (2023 – 2025)
- Built a testbed isolating one network factor at a time — ten Dockerized services, five application classes from video streaming and conferencing down to email and FTP — and used it to show augmentation is method-specific: the identical method that gains packet-size-sequence classifiers costs timestamp-based ones (IEEE IPCCC 2025).
Near-Switch Network Telemetry (NetEye) — Research Assistant, NextGArchLab (2022 – 2023)
- Broke the accuracy–scalability tradeoff in hybrid telemetry by replacing single-stream iterative refinement with near-switch window replay through every query, sustained across 15+ concurrent queries.
- Engineered a Delta+Huffman+LZ78 compression pipeline on FPGA to make replay affordable, and moved monitoring logic near-switch, cutting data-plane update latency by more than an order of magnitude.
Graph Neural Networks for Bug Prediction — SCAI group (Mar 2021 – Dec 2021)
- Built a GNN predicting bug locations in Python GitHub projects by combining code AST structure with GitHub issue text.
CAM2 Lab — Team Lead (2018 – 2020)
- Led a team on automated discovery of real-time network camera feeds from heterogeneous web pages — 57,364 cameras extracted from 237,257 pages — plus a feed health checker, image database, and camera-database API (ACM TOIT 2021; IEEE COMPSAC 2020).
Publications
3 first-author of 5 — full list on Google Scholar.
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.
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.
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.
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.
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.
Industry Experience
- SWE Intern, Carbonite (2019) — VM tooling in C#; Jenkins, vSphere/vCenter, PowerShell.
- SWE Intern, NextGear Capital (Cox Automotive) (2018) — rebuilt events server and React client over Postgres/Spark, Dockerized.
Teaching Experience
- Head Graduate Teaching Assistant (CS407), Purdue University (Jan 2022 – Present) — supervise and grade students building a group project in an Agile environment.
- Graduate Teaching Assistant (CS180), Purdue University (summers, Jan 2022 – Present) — guide undergraduate lab students applying object-oriented programming in Java.
- Graduate Grading Teaching Assistant (CS130), UCLA (Jan 2021 – Jun 2021) — graded programs and exams for software engineering.
Skills
- Machine learning: anomaly detection, deep learning, explainable AI (XAI), GNNs, federated and distributed learning, RAG / retrieval, sequence modeling, computer vision
- Security & systems: intrusion detection, traffic classification, adversarial evaluation, digital-twin simulation, network telemetry, UAV / FANET security
- Engineering: PyTorch, TensorFlow, data and training pipelines, edge / low-latency deployment, large-scale dataset generation, experiment design
- Languages & tools: Python, C++, Java, JavaScript; Git, Linux, Docker, REST APIs, network simulation, FPGA prototyping
Awards and Honors
- Boyce Graduate Teacher Award, Purdue University (2024)
- Bachelor’s Degree with Honors, Purdue University
- Dean’s Honor List, Purdue University
- Best Sophomore Award in Computer Science, Purdue University