相关论文: Differentially Private Multimodal In-Context Learn…

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only…

Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local…

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been…

Video crime detection is a significant application of computer vision and artificial intelligence. However, existing datasets primarily focus on detecting severe crimes by analyzing entire video clips, often neglecting the precursor…

Differentially private (DP) image synthesis aims to generate artificial images that retain the properties of sensitive images while protecting the privacy of individual images within the dataset. Despite recent advancements, we find that…

Mental health conditions, prevalent across various demographics, necessitate efficient monitoring to mitigate their adverse impacts on life quality. The surge in data-driven methodologies for mental health monitoring has underscored the…

Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive, there is a key challenge in designing privacy-preserving…

Prompt privacy is crucial, especially when using online large language models (LLMs), due to the sensitive information often contained within prompts. While LLMs can enhance prompt privacy through text rewriting, existing methods primarily…

Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the…

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Perception is a fundamental task in the field of computer vision, encompassing a diverse set of subtasks that can be systematically categorized into four distinct groups based on two dimensions: prediction type and instruction type.…

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy…

Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is…

Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…

Parameter efficient transfer learning (PETL) is an emerging research spot that aims to adapt large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage and computation costs. However,…

Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks. Many existing methods resort to the…

This paper considers the problem of differentially private semi-supervised transfer and multi-task learning. The notion of \emph{membership-mapping} has been developed using measure theory basis to learn data representation via a fuzzy…

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…