相关论文: Leveraging Per-Instance Privacy for Machine Unlear…

Differentially Private Stochastic Gradient Descent (DP-SGD) is a standard method for enforcing privacy in deep learning, typically using the Gaussian mechanism to perturb gradient updates. However, conventional mechanisms such as Gaussian…

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are often limited to…

Differentially private stochastic gradient descent (DP-SGD) has been widely adopted in deep learning to provide rigorously defined privacy, which requires gradient clipping to bound the maximum norm of individual gradients and additive…

The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a…

Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted. Machine learning (ML) exacerbates this problem because any model trained with said data may have memorized it,…

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models…

Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model predictions, e.g., for minority groups. Gradient clipping,…

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…

Large Language Models (LLMs) trained on extensive datasets often learn sensitive information, which raises significant social and legal concerns under principles such as the "Right to be forgotten." Retraining entire models from scratch to…

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Machine unlearning is the process of removing the imprint left by specific data samples during the training of a machine learning model. AI developers, including those building personalized technologies, employ machine unlearning for…

Despite intense interest and considerable effort, the current generation of neural networks suffers a significant loss of accuracy under most practically relevant privacy training regimes. One particularly challenging class of neural…

We study the problem of unlearning datapoints from a learnt model. The learner first receives a dataset $S$ drawn i.i.d. from an unknown distribution, and outputs a model $\widehat{w}$ that performs well on unseen samples from the same…

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…

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been suggested for differentially private learning. While previous research provides differential privacy bounds for SGLD at the initial steps of the algorithm or when…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training. (Here, public data refers to auxiliary data sets that have no privacy…

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely…