Differentially private optimization on large model at small cost
Differentially private (DP) optimization is the standard paradigm to learn large neural
networks that are accurate and privacy-preserving. The computational cost for DP deep …
networks that are accurate and privacy-preserving. The computational cost for DP deep …
Llm-pbe: Assessing data privacy in large language models
Large Language Models (LLMs) have become integral to numerous domains, significantly
advancing applications in data management, mining, and analysis. Their profound …
advancing applications in data management, mining, and analysis. Their profound …
Explaining the model, protecting your data: Revealing and mitigating the data privacy risks of post-hoc model explanations via membership inference
Predictive machine learning models are becoming increasingly deployed in high-stakes
contexts involving sensitive personal data; in these contexts, there is a trade-off between …
contexts involving sensitive personal data; in these contexts, there is a trade-off between …
ExpShield: Safeguarding Web Text from Unauthorized Crawling and Language Modeling Exploitation
As large language models (LLMs) increasingly depend on web-scraped datasets, concerns
over unauthorized use of copyrighted or personal content for training have intensified …
over unauthorized use of copyrighted or personal content for training have intensified …