Search Results for author:
Found 9 papers, 4 papers with code
Closed-Form Bounds for DP-SGD against Record-level Inference
This paper presents a new approach to evaluate the privacy of machine learning models against specific record-level threats, such as membership and attribute inference, without the indirection through DP.
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
In this paper, we take an information flow control perspective to describe machine learning systems, which allows us to leverage metadata such as access control policies and define clear-cut privacy and confidentiality guarantees with interpretable information flows.
Analyzing Leakage of Personally Identifiable Information in Language Models
Understanding the risk of LMs leaking Personally Identifiable Information (PII) has received less attention, which can be attributed to the false assumption that dataset curation techniques such as scrubbing are sufficient to prevent PII leakage.
Bayesian Estimation of Differential Privacy
Our Bayesian method exploits the hypothesis testing interpretation of differential privacy to obtain a posterior for $\varepsilon$ (not just a confidence interval) from the joint posterior of the false positive and false negative rates of membership inference attacks.
Differentially Private Model Compression
Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models for many downstream Natural Language Processing (NLP) tasks while simultaneously guaranteeing differential privacy.
Differentially Private Fine-tuning of Language Models
For example, on the MNLI dataset we achieve an accuracy of $87. 8\%$ using RoBERTa-Large and $83. 5\%$ using RoBERTa-Base with a privacy budget of $\epsilon = 6. 7$.
Numerical Composition of Differential Privacy
We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy.
Training Data Leakage Analysis in Language Models
It has been demonstrated that strong performance of language models comes along with the ability to memorize rare training samples, which poses serious privacy threats in case the model is trained on confidential user content.
Analyzing Information Leakage of Updates to Natural Language Models
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models.
