Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Paper
•
2601.15220
•
Published
•
8
AI & ML interests
LLM, trustworthy AI, AI security, privacy, calibration, hallucination
Recent Activity
View all activity
Papers
Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models
Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
mgubri
authored
a
paper
4 days ago
mgubri
updated
a
collection
4 days ago
mgubri
submitted
a
paper
to Daily Papers
4 days ago
mgubri
authored
a
paper
3 months ago
mgubri
updated
a
collection
3 months ago
mgubri
authored
a
paper
3 months ago
mgubri
updated
2
collections
3 months ago
ahmedheakl
authored
a
paper
3 months ago
mgubri
authored
a
paper
4 months ago
ahmedheakl
authored
a
paper
4 months ago
haritzpuerto
updated
2
datasets
4 months ago
tommaso-green
authored
4
papers
4 months ago
Massively Multilingual Lexical Specialization of Multilingual Transformers
Paper
•
2208.01018
•
Published
•
1
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications
Paper
•
2403.05303
•
Published
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
Paper
•
2506.15674
•
Published
•
2
C-SEO Bench: Does Conversational SEO Work?
Paper
•
2506.11097
•
Published
•
2
mgubri
authored
3
papers
5 months ago