🎓 I'm currently a PhD candidate at the University of Basel, Switzerland, working in the intersection of Machine Learning and Security/Privacy.

My current research primarily focuses on:

• Privacy-preserving Machine Learning, especially:
  • DP-Morph: Improving the Privacy-Utility-Performance Trade-off for Differentially Private OCT Segmentation (https://github.com/ShivaP69/DP_Morph) or (https://gitlab.com/dmi-pet-public/parsarad2025dp-morph)
  • Attacks and privacy concerns in recommender systems (https://gitlab.com/dmi-pet-public/Parsarad2025privacy)
  • Membership inference attacks in medical imaging
  • Attacks and privacy concerns in recommender systems
• Evaluating computational trade-offs in Differential Privacy (e.g., DPSGD variants)
• Bias in COVID-19 Models (dataset and codes:https://zenodo.org/records/7997151)

I supervise Master's and Bachelor's students on topics related to ML, security, and privacy. Some of the recent projects I’ve supervised include:

• 🔍 Are Optical Coherence Tomography (OCT) images unique biometric identifiers?
• 🤖 Automated Analysis of Smart Toy Privacy Policies using LLMs
• 🧾 Privacy Policy Analysis with Large Language Models
• 💻 Evaluating new DPSGD variants for computational efficiency

• Languages: Python
• ML/AI: PyTorch, TensorFlow
• Security/Privacy: Differential Privacy, Adversarial ML, Inference Attacks
• Domains: Medical Imaging, Recommender Systems, Privacy Policy Analysis, LLMs

• ✉️ Email

Feel free to connect or reach out.