Securing the Future of Autonomous Clinical Intelligence.

I am a principal researcher and security engineer working at the convergence of Medical Artificial Intelligence and Offensive/Defensive Cybersecurity.

Modern healthcare increasingly relies on deep neural architectures—from 3D Vision Transformers parsing volumetric CT/MRI scans to clinical foundation models assisting diagnostic triage. Yet these models operate inside interconnected hospital networks and remain vulnerable to imperceptible adversarial perturbations, DICOM parser memory corruption, and gradient inversion attacks.

My research focuses on three core problems: (1) provably robust 3D medical segmentation under bounded L-infinity perturbations, (2) kernel-level eBPF & Rust sandboxing for untrusted AI inference workloads, and (3) differentially private federated learning across multi-institutional clinical cohorts.

Research Focus Areas

01

Adversarial Robustness in 3D Volumetric Imaging

Designing certified randomized smoothing and spectral-regularized 3D Vision Transformers (Swin-UNETR) resilient to PGD and frequency-domain perturbations in MRI/CT volumes.

02

eBPF Runtime Telemetry & Memory-Safe Sandboxing

Eliminating parser exploits in clinical DICOM gateways and isolating untrusted model execution using Linux Landlock, seccomp-bpf, and ring-buffer eBPF probes.

03

Federated Clinical Learning & Gradient Defense

Preventing patient reconstruction attacks from shared model gradients using Rényi Differential Privacy (RDP) and secure aggregation protocols.

Experience

2024 — Present
Principal Research Scientist (Medical AI & Security)
Synapse Security & Clinical AI Lab

Leading cross-disciplinary research on adversarial robustness for FDA SaMD radiology pipelines and zero-trust inference enclaves.

2021 — 2024
Staff Security Researcher (AI Infrastructure)
Aegis Systems Defense

Architected eBPF-based runtime enforcement for GPU compute clusters and discovered multiple critical CVEs in medical imaging parsers.

2017 — 2021
Ph.D. in Computer Science (Adversarial ML & Medical Imaging)
Institute for Computational Medicine

Dissertation on certified robustness bounds for volumetric brain tumor segmentation in multi-modal 3T MRI.

Selected Publications

01 — 2026 · MICCAI / IEEE Transactions on Medical Imaging
Spectral-Norm Regularized 3D Swin Transformers Against Imperceptible Volumetric Perturbations in Clinical MRI
PDF →
02 — 2025 · USENIX Security Symposium
Zero-Trust PACS: Mitigating Heap Overflow Exploits in Legacy C++ DICOM Parsers via Rust FFI & eBPF Containment
PDF →
03 — 2025 · NeurIPS Workshop on Privacy in Machine Learning
Sub-Gaussian Rényi Differential Privacy Bounds for Multi-Center Oncology Federated Learning
PDF →

Contact

For coordinated vulnerability disclosures in medical devices or clinical AI pipelines, academic collaborations, or editorial inquiries, use encrypted email below. Content on this page is managed via Payload CMS (/admin).

PGP //4F9A 8C12 E7B0 31D4 992A 7E11 C0DE 8841 B209 6F1C