Franziska Boenisch

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

International Conference on Learning Representations (ICLR)

Annual Meeting of the Association for Computational Linguistics (ACL)
On the Privacy Risk of In-context Learning

Privacy Enhancing Technologies Symposium (PETS)
A Unified Framework for Quantifying Privacy Risk in Synthetic Data

Privacy Enhancing Technologies Symposium (PETS)
Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees.

IEEE European Symposium on Security and Privacy (EuroS&P)
When the Curious Abandon Honesty: Federated Learning Is Not Private

IEEE European Symposium on Security and Privacy (EuroS&P)
Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation

International Conference on Learning Representations (ICLR)
Sentence Embedding Encoders are Easy to Steal but Hard to Defend

Conference on Neural Information Processing Systems (NeurIPS)
Have it your way: Individualized Privacy Assignment for DP-SGD

International Conference on Learning Representations (ICLR)
Stealing and Defending Transformer-based Encoders