Related papers: How Does Differential Privacy Affect Social Bias i…
Graphs offer unique insights into relationships between entities, complementing data modalities like text and images and enabling AI models to extend their capabilities beyond traditional tasks. However, learning from graphs often involves…
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…
Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…
We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…
Collecting and analyzing massive data generated from smart devices have become increasingly pervasive in crowdsensing, which are the building blocks for data-driven decision-making. However, extensive statistics and analysis of such data…
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due to the need to capture complex structures under noisy…
Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a…
Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level,…
While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cross-silo FL, a setting characterized by a limited number of…
The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science. However, concerns regarding data privacy have emerged,…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Differentially private (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its non-private counterpart. To analyze the convergence of DP…
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To…
In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…
This paper considers subject level privacy in the FL setting, where a subject is an individual whose private information is embodied by several data items either confined within a single federation user or distributed across multiple…
Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…
Differential Privacy (DP) is a formal definition of privacy that provides rigorous guarantees against risks of privacy breaches during data processing. It makes no assumptions about the knowledge or computational power of adversaries, and…
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…
Differentially private (DP) synthetic data is a promising approach to maximizing the utility of data containing sensitive information. Due to the suppression of underrepresented classes that is often required to achieve privacy, however, it…