About Me
Sai Puppala is an Assistant Professor in the Department of Computer Science and Engineering at
New Mexico Tech, working at the intersection of Artificial Intelligence (AI),
Machine Learning (ML), and cybersecurity. His research focuses on developing robust, adaptive,
and secure intelligent systems addressing contemporary challenges in cybersecurity and data
integrity, particularly in dynamic and resource-constrained environments. He earned his Ph.D. in
Computer Science from Southern Illinois University Carbondale, where he was a
member of the Security
and Privacy Enhanced Machine Learning (SUPREME) Lab, advised by Dr. Sajedul Talukder and
Dr. Koushik Sinha.
Prior to joining New Mexico Tech, Sai was a Senior Research Software Engineer at
John Deere, where he applied his expertise in Big Data, Machine Learning, and
Cloud Services to solve complex problems across Manufacturing, Transportation, and Healthcare
domains. He has authored over 55 peer-reviewed publications in prestigious
journals and top-tier conferences including IEEE COMPSAC, IEEE/ACM ASONAM, ICWSM, and the
American Nuclear Society.
Research Interests
- Federated Learning — secure, communication-efficient, and adaptive federated learning for resource-constrained environments
- Agentic AI and Multi-Agent Systems — autonomous agents capable of planning, tool use, and multi-step reasoning, with coordination and communication protocols for collaborative task execution
- Adversarial Machine Learning and LLM Safety — jailbreak and prompt-injection defenses, data poisoning and evasion attacks, red-teaming, and alignment evaluation for foundation models
- Robust and Trustworthy AI — uncertainty quantification, interpretability, fairness, and reliability under distribution shift and noisy real-world conditions
- Applied AI for Safety-Critical Systems — predictive analytics and anomaly detection for healthcare, critical infrastructure, and other high-stakes deployment settings
- Quantum Cryptography — quantum key distribution, post-quantum cryptographic protocols, and quantum-inspired models for securing next-generation networks
Recent News
- 2025Six papers accepted in American Nuclear Society top journal
- 2025Five papers accepted at ANS I&P 2025
- 2025Won Best Reviewer Award — top 4% among 497 reviewers at ICWSM 2025
- 2025Served as Meta Reviewer for PacificVis 2025
- 2025Awarded Grant Writing Certificate from University of Georgia
- 2024Paper accepted in MDPI Agriculture (Impact Factor: 3.8)
- 2024Four papers accepted at COMPSAC 2024 (acceptance rate: 22%)
- 2024Paper accepted at ICMLA 2024 (acceptance rate: 18%)
- 2024Four papers accepted at ASONAM 2024 (acceptance rate: 25%)
- 2024Paper accepted at ICWSM 2024 (acceptance rate: 12%)
- 2024Seven book chapters published in Data-driven Approaches to Medical Imaging, Springer
- 2024Honored with John Deere Presidents Award, CIO Global IT Impact Award, and VP After Market Award
- 2024Awarded AWS Associate ML and AWS Solutions Architect certifications
- 2023Three papers accepted at ACM/IEEE ASONAM 2023
Publications
You can also find my articles on my Google Scholar profile.
Work in Progress
Sai Puppala. (In progress). A Bayesian Gaussian Approach to Personalized Federated Learning through Dynamic-UMAP Enhanced Variational Interference.
Sai Puppala. (In progress). Survey on Advances in Federated Learning for Resource-Constrained IoT Devices with LEO Satellite Integration.
Accepted — Pending Publication
Sai Puppala et al. (2025). Securing SDN-Based Advanced Reactors Against DDoS Attacks Using Quantum-Inspired Ensemble Models. Nuclear Plant Instrumentation and Control & Human-Machine Interface, ANS.
Sai Puppala et al. (2025). Proactive Cybersecurity Framework for Nuclear Power Plants Using Quantum Large Language Models. Nuclear Plant Instrumentation and Control & Human-Machine Interface, ANS.
Sai Puppala et al. (2025). A Privacy-Aware Cyber Attack Detection Framework for Advanced Reactors Using Data Fusion and Quantum Deep Learning. Nuclear Plant Instrumentation and Control & Human-Machine Interface, ANS.
Sai Puppala et al. (2025). Secure Anomaly Detection in Advanced Reactor through Quantum Federated Learning with Advanced Cryptography. Nuclear Plant Instrumentation and Control & Human-Machine Interface, ANS.
Sai Puppala et al. (2025). LLM-Powered Chatbot for Safety Compliance Assistance in Nuclear Power Plants. Nuclear Plant Instrumentation and Control & Human-Machine Interface, ANS.
Sai Puppala et al. (2025). Optimus-Q: Utilizing Blockchain Federated Learning in Adaptive Human Robots for Intelligent NPP Operations through Quantum Cryptography. ANS.
Sai Puppala et al. (2025). Blockchain for Identity Governance: Policy Enforcement and Compliance in IAM Systems. Springer Nature.
Published Works
Sai Puppala et al. (2024). A Visual Approach to Tracking Emotional Sentiment Dynamics in Social Network Commentaries.
18th International AAAI Conference on Web and Social Media (ICWSM 2024).
Sai Puppala et al. (2024). Generative Adversarial Networks for Data Augmentation. In
Data Driven Approaches on Medical Imaging, Springer.
Sai Puppala et al. (2024). Adaptive Machine Learning-Based Threat Intelligence in Nuclear Facilities (AML-TIN): A Framework for Enhanced Cybersecurity in Nuclear Computing Environments.
Transactions of the American Nuclear Society.
Sai Puppala et al. (2024). SocialGuard: Bangla Text-Based Gender Identification for Enhancing Integrity in Social Networks.
48th IEEE International Conference on Computers, Software, and Applications (COMPSAC 2024).
Sai Puppala et al. (2024). SCALE: Self-regulated Clustered federAted LEarning in a Homogeneous Environment.
IEEE COMPSAC 2024.
Sai Puppala et al. (2024). Towards Communication-Efficient Federated Learning Through Particle Swarm Optimization and Knowledge Distillation.
IEEE COMPSAC 2024.
Sai Puppala et al. (2024). SCAN: A HealthCare Personalized ChatBot with Federated Learning Based GPT.
IEEE COMPSAC 2024.
Sai Puppala et al. (2024). Advancements in Multimodal Social Media Post Summarization: Integrating GPT-4 for Enhanced Understanding.
IEEE COMPSAC 2024.
Sai Puppala et al. (2024). SocFedGPT: Federated GPT-based Adaptive Content Filtering System Leveraging User Interactions in Social Networks.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). 4WHContext: A Context Based Hate Speech Detection Framework From Social Media Posts.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). SocialRec: User Activity Based Post Weighted Dynamic Personalized Post Recommendation System in Social Media.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). Bangla Emotion Detection Dataset With An Extended Taxonomy And Its Evaluation.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). EVOLVE: Predicting User Evolution and Network Dynamics in Social Media Using Fine-Tuned GPT-like Model.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). Combating Echo Chambers In Online Social Network By Increasing Content Diversity In Recommendation.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). CAMERA: Context Based Emotion Detection Framework And Its Evaluation.
IEEE/ACM ASONAM 2024.
Sai Puppala et al. (2024). Towards Federated Learning Based Contraband Detection Within Airport Baggage X-Rays.
International Conference on Machine Learning & Applied Network Technologies (ICMLANT 2024).
Sai Puppala et al. (2023). Blockchain-Integrated Secure Framework for Enhanced E-Government Services. In
Building Cybersecurity Applications with Blockchain and Smart Contracts.
Sai Puppala et al. (2023). Monitoring Dynamics of Emotional Sentiment in Social Network Commentaries.
IEEE/ACM ASONAM 2023.
Sai Puppala et al. (2023). Combating Identity Attacks in Online Social Networks: A Multi-Layered Framework Using Zero-Knowledge Proof and Permissioned Blockchain.
IEEE/ACM ASONAM 2023.
Sai Puppala et al. (2022). Machine Learning and Sentiment Analysis for Predicting Environmental Lead Toxicity in Children at the ZIP Code Level.
IEEE International Conference on AI in Cybersecurity (ICAIC 2022).
Sai Puppala et al. (2022). Collaborative Differentially Private Federated Learning Framework for the Prediction of Diabetic Retinopathy.
IEEE ICAIC 2022.
Sai Puppala et al. (2022). Prediction of Childhood and Pregnancy Lead Poisoning Using Deep Learning.
Journal of Computing Sciences in Colleges.
Sai Puppala et al. (2022). A Novel Hierarchical Federated Learning with Self-Regulated Decentralized Clustering.
Journal of Computing Sciences in Colleges.
Teaching
Assistant Professor - New Mexico Tech
CSCI-5089/CYBS-5005/CSCI-4011 — Data Science for Cybersecurity
New Mexico Tech, Socorro, NM · 2026 – Present
Introduction to Data Science, Data Collection and Cleaning, Exploratory Data Analysis, Statistical Foundations, Data Visualization, Machine Learning Fundamentals, Model Evaluation and Validation, Tools and Platforms, Ethics and Data Privacy, Communicating Results, Hands-On Project.
Corporate Training
CS508 — Generative Artificial Intelligence
Corporate Trainer · John Deere University, Moline, IL · 2024 – 2026
Introduction to Generative AI, Key Concepts and Terminology, Types of Generative Models, Applications in Business, Ethical Considerations, Tools and Platforms, Implementing GenAI in the Workplace, Future Trends, Hands-On Session.
Teaching Assistant — Southern Illinois University
CS 330/CS 491 — Intro to the Design and Analysis of Algorithms
Teaching Assistant · Spring 2024
Design, implementation, complexity and limitations of algorithms. Methods for algorithm analysis and correctness proofs.
CS 409/CS 591 — Ethical Hacking
Teaching Assistant · Fall 2023
Introduction to Ethical Hacking, Legal and Ethical Considerations, Exploitation Techniques, Web Application Security, Network Security and Penetration Testing, Wireless Security, Tools including Metasploit and Wireshark, Case Studies.
CS 330/CS 491 — Intro to the Design and Analysis of Algorithms
Teaching Assistant · Spring 2023
Design, implementation, complexity and limitations of algorithms. Methods for algorithm analysis and correctness proofs.
CS 409/CS 591 — Ethical Hacking
Teaching Assistant · Fall 2022
Introduction to Ethical Hacking, Legal and Ethical Considerations, Exploitation Techniques, Web and Network Security, Wireless Security, Industry tools.
Course Trainer — Yaaltech Institute, Hyderabad, India (2015–2018)
CS400 — Big Data Cloud Services
Course Trainer
Big Data Concepts, Cloud Computing Integration, Data Ingestion and Processing, Cloud-Based Storage, Analytics and Visualization, Real-Time Processing, Machine Learning in the Cloud, Security and Compliance, Cost Management, Case Studies.
CS200 — Introduction to Programming
Course Trainer
Programming Concepts, Variables and Data Types, Control Structures, Functions, Data Structures, Basic Algorithms, OOP Principles, IDEs and Version Control, Coding Best Practices.
Speaker Invitations
- TechWorld 2025 — Big Data, Computer Science, and Information Technologies
- GSPOWER 2026 — Global Summit on Power and Energy Engineering
- POWERMEET 2026 — 2nd International Meet & Expo on Power and Energy Engineering
- AGSCIVIL 2025 — Annual Global Summit on Civil, Structural, and Environmental Engineering
- TechFusion 2025 — AI, Cybersecurity, and Emerging Trends in Computer Science
- ICAIC 2025 — International Conference on Artificial Intelligence and Cybersecurity
- WSCSE-2026 — 2nd World Summit on Crop Science and Engineering
- ICMI 2025 — 27th ACM International Conference on Multimodal Interaction
- WEBNANO-2025 — 6th International Experts Meet on Nanoscience and Nanotechnology
- European Healthcare & Hospital Management Conference (2025)
- Nursing Asia-Pacific 2025 — 6th Asia-Pacific Advanced Nursing Practice Conclave