Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning
Explore secure participant selection in Federated Learning through Lotto, a system designed to protect against adversarial servers while maintaining efficient performance and privacy guarantees.
User-Level and Federated Local Differential Privacy in Statistical Inference
Explore fundamental statistical inference challenges in distributed data systems with differential privacy constraints across servers and users, focusing on privacy-preserving information transmission.
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Explore how DP-SGD provides stronger privacy guarantees for similar datapoints in deep learning, revealing why common benchmarks leak less information than previously estimated.
Less is More: Revisiting the Gaussian Mechanism for Differential Privacy
Explore groundbreaking improvements to differential privacy through a novel Rank-1 Singular Multivariate Gaussian mechanism that enhances data protection while minimizing accuracy loss in high-dimensional queries.
Differentially Private Diffusion Probabilistic Models for Image Synthesis
Explore how dp-promise leverages diffusion model noise to achieve differential privacy in image synthesis while maintaining high image quality and protecting sensitive training data.
Evaluating the Usability of Differential Privacy Tools with Data Practitioners
Explore the usability evaluation of four Python-based differential privacy tools through a comprehensive study of 24 data practitioners, revealing key insights for improving implementation and adoption.
Black Hat Europe 2024
Black Hat Europe 2024