TabPATE: Differentially Private Tabular In-Context Learning Without Public Data
Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We first show that even basic membership inference attacks succeed against tabular ICL, motivating formal privacy protection. We then introduce TabPATE, a differentially private PATE-style defense for tabular ICL that does not require public in-distribution data. TabPATE partitions the private context across teacher models, privately aggregates their labels on synthetic tabular queries, and releases the resulting labeled
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Federated Learning Could Train AI Language Models Without Sharing Private Data - Bioengineer.org →
- FuzzySimilar title/name (fuzzy) · 84%amitness/learning →
“Fuzzy title match (0.92): “TabPATE: Differentially Private Tabular In-Context Learning ” ≈ “amitness/learning””
- PossiblePossibly related (embedding) · 57%meta-pytorch/opacus →
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “TabPATE: Differentially Private Tabular In-Context Learning ” ≈ “aymericdamien/TopDeepLearning””
- PossiblePossibly related (embedding) · 53%A machine learning framework for early warning prediction of student success using privacy preserving synthetic educational data - Nature →