Research Interests

My research focuses on the intersection of machine learning and security. I’m particularly interested in:

• Machine Learning Security: Understanding and defending against adversarial attacks on machine learning models
• Secure ML Applications: Developing robust machine learning systems for security-critical applications
• Privacy-Preserving ML: Methods for training and deploying models while protecting sensitive data

Current Projects

Working with researchers at the Ensure Research Lab, I’m currently investigating novel attack vectors and defenses for deep learning systems.

Publications

2023

• Smith, J., Sandoval, G., et al. “Robust Defenses Against Adversarial Attacks in Vision Transformers.” IEEE Symposium on Security and Privacy (S&P).

2022

• Jones, A., Sandoval, G., et al. “Privacy-Preserving Machine Learning: Challenges and Opportunities.” ACM Conference on Computer and Communications Security (CCS).

Collaborations

I’m always interested in collaborating with other researchers in the fields of machine learning, security, and operating systems. Feel free to reach out if you’re working on related problems.