Skip to content
Param Desai

Publications

Peer-reviewed research across IEEE, Springer, and international venues.

6 papers · 5 IEEE venues · 2025–2026
Year:
Area:
2026
AI2M4RI 2026 Accepted

Machine Unlearning-based Privacy-First Medical Imaging Framework for TB Detection

Proposes a privacy-first machine unlearning approach for medical imaging, allowing TB detection models to forget patient data on demand while preserving diagnostic performance.

Machine UnlearningHealthcare AI
2025
Springer CML 2025 Published

Explainable AI and Quantum Security for Smart Homes Network Attack Classification

Combines explainable AI techniques with quantum cryptographic primitives for classifying and interpreting network attacks in smart home IoT environments.

XAIQuantum SecurityCybersecurity
2025
IEEE ICSC 2025 Presented

Deep Learning and Explainable AI Framework for False Data Injection Attack Detection in Autonomous Vehicles

Develops a deep learning pipeline with integrated SHAP-based explainability for detecting false data injection attacks in autonomous vehicle sensor networks, providing both accuracy and interpretable model decisions.

* Presented in person at Tampa, Florida, USA

XAICybersecurity
2025
IEEE VTC Spring 2025 Published

Q-ShielD: CV-QKD Framework for Secure Autonomous Vehicle Communications

Introduces a continuous-variable quantum key distribution framework for securing V2X communications in autonomous vehicle networks against eavesdropping and quantum-level adversarial attacks.

Quantum SecurityCybersecurity
2025
IEEE HealthCom 2025 Published

Quantum-Based Edge Intelligence Framework for IoT Healthcare Systems

Presents a quantum-assisted edge computing framework for real-time anomaly detection and secure data processing in IoT-enabled healthcare environments.

Quantum SecurityIntelligent SystemsIoT
2025
IEEE GLOBECOM 2025 Accepted

Quantum-Secured Explainable Machine Unlearning for Phishing Detection in IoT

Proposes a quantum-secured machine unlearning framework that enables IoT devices to selectively forget phishing-related training data while maintaining detection accuracy, using explainability techniques to audit the unlearning process.

Machine UnlearningCybersecurityXAI