LLM-CEG applies differential privacy during fine-tuning of DistilGPT-2 to reduce membership inference attack success by 71.5% while increasing out-of-distribution utility by 47-50%.
Human-centered privacy framework for AI systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models
LLM-CEG applies differential privacy during fine-tuning of DistilGPT-2 to reduce membership inference attack success by 71.5% while increasing out-of-distribution utility by 47-50%.