Fine-tuned LLMs leak private fragment-level information to adversaries holding only a few unordered public fragments, as shown by two probe attacks (LR-Attack and PRISM) on medical and legal summarization tasks.
Security and privacy challenges of large language models: A survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fragments to Facts: Partial-Information Fragment Inference from LLMs
Fine-tuned LLMs leak private fragment-level information to adversaries holding only a few unordered public fragments, as shown by two probe attacks (LR-Attack and PRISM) on medical and legal summarization tasks.