PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
This paper proposes a five-dimension ethical design space for front-end biometric translation in sensor-fused health AI agents, including adaptive disclosure as a guardrail against hallucinations and biofeedback loops.
Creates MediLongChat synthetic longitudinal medical dialogues and benchmarks showing state-of-the-art LLMs struggle with in-dialogue, cross-dialogue, and synthesis reasoning tasks.
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
citing papers explorer
-
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
PII can be reconstructed from SFT models via prefix attacks, with the new COVA algorithm improving success rates and leakage varying by attacker knowledge and PII type.