SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks

arXiv:2403.08481v1 Announce Type: new
Abstract: Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary datasets. This fine-tuning data is especially likely to contain personal or sensitive information about individuals, resulting in increased privacy risk. Membership inference attacks are the most commonly employed attack to assess the privacy leakage of a machine learning model. However, limited research is available …

abstract applications arxiv attacks cs.lg data datasets fine-tuning inference language language models language processing natural natural language natural language processing processing proprietary proprietary datasets them type vulnerability