相关论文: From Privacy to Generalization: Linear Max-Informa…

We provide novel information-theoretic generalization bounds for stochastic gradient Langevin dynamics (SGLD) under the assumptions of smoothness and dissipativity, which are widely used in sampling and non-convex optimization studies. Our…

Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness.…

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…

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…

Gaussian Processes (GPs) are a generic modelling tool for supervised learning. While they have been successfully applied on large datasets, their use in safety-critical applications is hindered by the lack of good performance guarantees. To…

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…

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,…

In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorithm is bounded from above by a function of the relative…

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privacy costs across training steps. The equivalent privacy costs…

Differential Privacy (DP) is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior…

Decentralized Learning (DL) enables users to collaboratively train models without sharing raw data by iteratively averaging local updates with neighbors in a network graph. This setting is increasingly popular for its scalability and its…

We consider the problem of generating private synthetic versions of real-world graphs containing private information while maintaining the utility of generated graphs. Differential privacy is a gold standard for data privacy, and the…

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly…

We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for…

Differential privacy (DP) is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian…

We consider three different variants of differential privacy (DP), namely approximate DP, R\'enyi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint…

Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the specific properties of the velocity field associated with…

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…