Portfolio

Our research contributions, publications, and technical achievements in quantum-resilient cybersecurity

Research Papers

QGuardian: A Federated Learning Framework for Quantum-Resilient Anomaly Detection in Cybersecurity
Research Team: Ahaan Thota., Saketh Tammisetti
TechRxiv, January 2026
This paper presents QGuardian, a comprehensive quantum-resilient cybersecurity framework that combines federated learning, post-quantum cryptography, and blockchain verification to provide predictive cyber defense. The system enables real-time anomaly detection across distributed networks while preserving data privacy and ensuring security against both classical and quantum attacks.

Projects & Achievements

🤖

Federated Learning Framework

2025 - Present

Developed a privacy-preserving federated learning system using TensorFlow Federated (TFF) with FedAvg aggregation for distributed anomaly detection across multiple organizations.

Machine Learning Privacy TensorFlow
Learn More
🔐

Post-Quantum Cryptography

2025 - Present

Implemented Kyber KEM (Key Encapsulation Mechanism) for post-quantum encryption, ensuring secure communication channels resistant to quantum computing attacks.

Cryptography Quantum-Safe Kyber KEM
Learn More
⛓️

Blockchain Verification System

2025 - Present

Built an immutable blockchain ledger for tamper-proof event logging, cryptographic signatures, and integrity verification of security events and model updates.

Blockchain Security Verification
Learn More
🎯

Real-Time Anomaly Detection

2025 - Present

Created an autoencoder-based anomaly detection system that provides real-time threat scoring and alerting with high accuracy and low false positive rates.

AI/ML Anomaly Detection Real-Time
Learn More
🔬

Research & Development

2025 - Present

Ongoing research in quantum-resistant security, federated learning optimization, and blockchain-based verification systems for next-generation cybersecurity.

Research Innovation Development
View Research
🏆

Technical Innovation

2025 - Present

Pioneering the integration of three critical security layers: federated learning for privacy, post-quantum encryption for future-proofing, and blockchain for transparency.

Innovation Integration Security
View System

Technical Stack

🐍

Python

Core development language for machine learning, cryptography, and blockchain implementation.

Python 3 Development
🧠

TensorFlow Federated

Federated learning framework for privacy-preserving distributed machine learning.

TFF Federated Learning
🔒

Post-Quantum Cryptography

Kyber KEM and lattice-based cryptographic algorithms for quantum-resistant security.

PQC Kyber
⛓️

Blockchain Technology

Custom blockchain implementation for immutable event logging and verification.

Blockchain Ledger