activity
20222025
most citedAnalyzing Leakage of Personally Identifiable Information in Language Models

13 citations · 33 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR2025★ 4 cited

Securing AI Agents with Information-Flow Control

Manuel Costa, Boris Köpf, Aashish Kolluri +6

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of i…

cs.CL2025★ 1 cited

The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text

Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-Béguelin +2

How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthe…

cs.LG2023★ 1 cited

Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective

Lukas Wutschitz, Boris Köpf, Andrew Paverd +6

Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during traini…

cs.LG2023★ 13 cited

Analyzing Leakage of Personally Identifiable Information in Language Models

Nils Lukas, Ahmed Salem, Robert Sim +3

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs…

cs.LG2022★ 4 cited

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Ahmed Salem, Giovanni Cherubin, David Evans +5

Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of in…

cs.LG2022★ 10 cited

Bayesian Estimation of Differential Privacy

Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +6

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that su…