相关论文: Does Differential Privacy Impact Bias in Pretraine…

Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training these models on user-written code introduces significant…

Recent work in Differential Privacy with Natural Language Processing (DP NLP) has proposed numerous promising techniques in the form of text rewriting mechanisms. In the evaluation of these mechanisms, an often-ignored aspect is that of…

Federated learning (FL) enables organizations to collaboratively train models without sharing their datasets. Despite this advantage, recent studies show that both client updates and the global model can leak private information, limiting…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

Estimating causal effects from randomized experiments is only possible if participants are willing to disclose their potentially sensitive responses. Differential privacy, a widely used framework for ensuring an algorithms privacy…

The remarkable proliferation of deep learning across various industries has underscored the importance of data privacy and security in AI pipelines. As the evolution of sophisticated Membership Inference Attacks (MIAs) threatens the secrecy…

Recent research has shown that structured machine learning models such as tree ensembles are vulnerable to privacy attacks targeting their training data. To mitigate these risks, differential privacy (DP) has become a widely adopted…

Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains…

Ensuring user privacy by synthesizing data from large language models (LLMs) tuned under differential privacy (DP) has become popular recently. However, the impact of DP fine-tuned LLMs on the quality of the language and the utility of the…

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

Many high-stakes applications require machine learning models that protect user privacy and provide well-calibrated, accurate predictions. While Differential Privacy (DP) is the gold standard for protecting user privacy, standard DP…

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are typically pretrained on large public datasets and then…

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for…

Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely…

Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data…

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…