14 papers
A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation
Stephen Meisenbacher, Angelo Kleinert, Florian Matthes
The goal of differentially private text obfuscation is to obfuscate, or "perturb", input texts with Differential Privacy (DP) guarantees, such that the private output texts are qua…
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Andreea-Elena Bodea, Stephen Meisenbacher, Florian Matthes
Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported utility of RAG-enabled insights…
Privacy Starts with UI: Privacy Patterns and Designer Perspectives in UI/UX Practice
Anxhela Maloku, Alexandra Klymenko, Stephen Meisenbacher +1
In the study of Human-Computer Interaction, privacy is often seen as a core issue, and it has been explored directly in connection with User Interface (UI) and User Experience (UX)…
SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
Andreea-Elena Bodea, Stephen Meisenbacher, Alexandra Klymenko +1
The continued promise of Large Language Models (LLMs), particularly in their natural language understanding and generation capabilities, has driven a rapidly increasing interest in…
With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting
Stephen Meisenbacher, Florian Matthes
Recent work in Differential Privacy with Natural Language Processing (DP NLP) has proposed numerous promising techniques in the form of text rewriting mechanisms. In the evaluation…
"We are not Future-ready": Understanding AI Privacy Risks and Existing Mitigation Strategies from the Perspective of AI Developers in Europe
Alexandra Klymenko, Stephen Meisenbacher, Patrick Gage Kelley +3
The proliferation of AI has sparked privacy concerns related to training data, model interfaces, downstream applications, and more. We interviewed 25 AI developers based in Europe…