Franziska Boenisch

Natural Identifiers for Privacy and Data Audits in Large Language Models

Data Provenance for Image Auto-Regressive Generation

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

TRACE: Transcoder-based Concept Editing

SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation

Distributed PATE and CaPC on a DIET: Private Knowledge Transfer without Public Data or Private Inference

BADI: Black-box and Anytime-valid Dataset Identification for Large Language Models

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning

Finding Dori: Memorization in Text-to-Image Diffusion Models Is Not Local

Adversarial Attacks and Defenses on Graph-aware Large Language Models

Stealing and Defending the Ends of LLMs

Differentially Private Federated Learning with Time-Adaptive Privacy Spending

BitMark: Watermarking Bitwise Autoregressive Image Generative Models

Memorization in Graph Neural Networks

Exploring the limits of strong membership inference attacks on large language models

Precise Parameter Localization for Textual Generation in Diffusion Models

Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs

Machine Unlearning for Contrastive Learning under Auditing

Captured by Captions: On Memorization and its Mitigation in CLIP Models

POST: A Framework for Privacy of Soft-prompt Transfer

Privacy Attacks on Image AutoRegressive Models

Unlocking Post-hoc Dataset Inference with Synthetic Data

Evaluating Model Robustness Against Unforeseen Adversarial Attacks

DP-GPL: Differentially Private Graph Prompt Learning

Lossgate: Incomplete Information and Misaligned Incentives Hinder Regulation of Societal Risks in Machine Learning