Send email Copy Email Address
Faculty

Franziska Boenisch

Research Group
Trustworthy Information Processing

Email

Address

Im Oberen Werk 1
66386 St. Ingbert (Germany)

Awards (selection)

2024: Busy Beaver Award "Differential Privacy: Mathematical Foundations and Applications in Machine Learning“, Saarland University

Further Information

Publications by Franziska Boenisch

Year 2024

2024-05-11

Memorization in Self-Supervised Learning Improves Downstream Generalization

Conference / Medium

International Conference on Learning Representations (ICLR)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2024

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Authors
Visit Detail Page
2024

Localizing Memorization in SSL Vision Encoders

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2024

Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page

Year 2023

2023-12-12

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

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-10-28

Learning to Walk Impartially on the Pareto Frontier of Fairness, Privacy, and Utility

Conference / Medium

Conference on Neural Information Processing Systems (NeurIPS)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-10-28

Regulation Games for Trustworthy Machine Learning

Conference / Medium

NeurIPS-Workshop (NeurIPS-W)

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-10-12

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

Article

CoRR

Tags
Trustworthy Information Processing
Authors
Visit Detail Page
2023-09-23

Evaluating Robustness to Unforeseen Adversarial Attacks

Article

ICLR

Tags
Trustworthy Information Processing
Authors
Full Paper Visit Detail Page
2023-07-10

Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees.

Conference / Medium

Privacy Enhancing Technologies Symposium (PETS)

Tags
Trustworthy Information Processing
Authors
Visit Detail Page