Related papers: Privatar: Scalable Privacy-preserving Multi-user V…
We study the computational cost of differential privacy in terms of memory efficiency. While the trade-off between accuracy and differential privacy is well-understood, the inherent cost of privacy regarding memory use remains largely…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
In modern datasets, where single records can have multiple owners, enforcing user-level differential privacy requires capping each user's total contribution. This "contribution bounding" becomes a significant combinatorial challenge.…
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived great success in many applications such as image…
Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms that achieve an optimal trade-off between privacy, utility and…
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…
Several companies (e.g., Meta, Google) have initiated "data-for-good" projects where aggregate location data are first sanitized and released publicly, which is useful to many applications in transportation, public health (e.g., COVID-19…
With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This…
More data is almost always beneficial for analysis and machine learning tasks. In many realistic situations however, an enterprise cannot share its data, either to keep a competitive advantage or to protect the privacy of the data sources,…
This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy…
Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are multiple sites holding…
Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic understanding of visual content, limiting their effectiveness in detecting…
Deep hash-based retrieval techniques are widely used in facial retrieval systems to improve the efficiency of facial matching. However, it also carries the danger of exposing private information. Deep hash models are easily influenced by…
We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…
Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized…
The collection of individuals' data has become commonplace in many industries. Local differential privacy (LDP) offers a rigorous approach to preserving privacy whereby the individual privatises their data locally, allowing only their…
In decentralized networks, nodes cannot ensure that their shared information will be securely preserved by their neighbors, making privacy vulnerable to inference by curious nodes. Adding calibrated random noise before communication to…
Reconstructing perceived images from human brain activity forms a crucial link between human and machine learning through Brain-Computer Interfaces. Early methods primarily focused on training separate models for each individual to account…
Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees essential. While differential privacy (DP) provides a principled framework for such…
In many industrial applications of big data, the Jaccard Similarity Computation has been widely used to measure the distance between two profiles or sets respectively owned by two users. Yet, one semi-honest user with unpredictable…