Faculty
Adam Dziedzic is a tenure-track faculty member at CISPA, where he co-leads the SprintML group with a research focus on Secure, Private, Robust, Interpretable, and Trustworthy Machine Learning. Before joining CISPA, he was a Postdoctoral Fellow at the Vector Institute and the University of Toronto, a member of the CleverHans Lab, advised by Prof. Nicolas Papernot. He earned his PhD in computer science at the University of Chicago, where he was advised by Prof. Sanjay Krishnan and worked on input and model compression for adaptive and robust neural networks.
ICML Workshop on Foundation Models in the WIld (ICML-W) POST: A Framework for Privacy of Soft-prompt Transfer
International Conference on Learning Representations (ICLR) Memorization in Self-Supervised Learning Improves Downstream Generalization
eBioMedicine Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
Conference on Neural Information Processing Systems (NeurIPS) Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Conference on Neural Information Processing Systems (NeurIPS) Localizing Memorization in SSL Vision Encoders
Conference on Neural Information Processing Systems (NeurIPS) Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives
Conference on Neural Information Processing Systems (NeurIPS) Robust and Actively Secure Serverless Collaborative Learning.
Conference on Neural Information Processing Systems (NeurIPS) Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Conference on Neural Information Processing Systems (NeurIPS) Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
CoRR Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders.