Related papers: DP-aware AdaLN-Zero: Taming Conditioning-Induced H…
Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…
Recently, due to the popularity of deep neural networks and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data privacy, there is a lot of interest in differentially…
Differential privacy is a widely accepted measure of privacy in the context of deep learning algorithms, and achieving it relies on a noisy training approach known as differentially private stochastic gradient descent (DP-SGD). DP-SGD…
While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…
We consider training models with differential privacy (DP) using mini-batch gradients. The existing state-of-the-art, Differentially Private Stochastic Gradient Descent (DP-SGD), requires privacy amplification by sampling or shuffling to…
Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…
Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. The combination of these two techniques, i.e., deep learning…
Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic…
As large language models (LLMs) increasingly underpin technological advancements, the privacy of their training data emerges as a critical concern. Differential Privacy (DP) serves as a rigorous mechanism to protect this data, yet its…
We study private prediction where differential privacy is achieved by adding noise to the outputs of a non-private model. Existing methods rely on noise proportional to the global sensitivity of the model, often resulting in sub-optimal…
Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-to-saddle dynamics, the impact of stochastic gradient…
In this work, we analyze the optimization behaviour of common private learning optimization algorithms under heavy-tail class imbalanced distribution. We show that, in a stylized model, optimizing with Gradient Descent with differential…
Differential privacy (DP) provides strong protection for sensitive data, but often reduces model performance and fairness, especially for underrepresented groups. One major reason is gradient clipping in DP-SGD, which can disproportionately…
When we enforce differential privacy in machine learning, the utility-privacy trade-off is different w.r.t. each group. Gradient clipping and random noise addition disproportionately affect underrepresented and complex classes and…
Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising…
Distributed machine learning (ML) training has become a necessity with the prevalence of billion to trillion-parameter-scale models. While prior work has improved training efficiency from the ML perspective at the application layer, it…
Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…
While the success of deep learning relies on large amounts of training datasets, data is often limited in privacy-sensitive domains. To address this challenge, generative model learning with differential privacy has emerged as a solution to…
When applying machine learning to medical image classification, data leakage is a critical issue. Previous methods, such as adding noise to gradients for differential privacy, work well on large datasets like MNIST and CIFAR-100, but fail…
Traditional Differentially Private Stochastic Gradient Descent (DP-SGD) introduces statistical noise on top of gradients drawn from a Gaussian distribution to ensure privacy. This paper introduces the novel Differentially Private Block-wise…