3 papers
cs.CR2026
LLM Anonymization Against Agentic Re-Identification
Ziwen Li, Jianing Wen, Tianshi Li
Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same deta…
cs.LG2025
Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
Jijie Zhou, Niloofar Mireshghallah, Tianshi Li
The rapid deployment of large language models (LLMs) in consumer applications has led to frequent exchanges of personal information. To obtain useful responses, users often share m…
cs.CR2025
Position: Privacy Is Not Just Memorization!
Niloofar Mireshghallah, Tianshi Li
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and…