Franziska Boenisch

European Conference on Artificial Intelligence (ECAI)
Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks

NeurIPS-Workshop (NeurIPS-W)
Auditing Empirical Privacy Protection for Adaptations of Large Language Models

ICML Workshop on Foundation Models in the WIld (ICML-W)
POST: A Framework for Privacy of Soft-prompt Transfer

IEEE International Symposium on Information Theory (ISIT)
Controlled privacy leakage propagation throughout differential private overlapping grouped learning

IEEE Journal on Selected Areas in Information TheoryControlled privacy leakage propagation throughout overlapping grouped learning

International Conference on Learning Representations (ICLR)
Memorization in Self-Supervised Learning Improves Downstream Generalization

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)
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders