Santiago Zanella-Beguelin

szanella's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 3 months ago

flwrlabs/Lizzy-7B

Text Generation • 7B • Updated May 28 • 544 • 29

upvoted a paper about 1 year ago

Securing AI Agents with Information-Flow Control

Paper • 2505.23643 • Published May 29, 2025 • 1

authored 3 papers about 1 year ago

Closed-Form Bounds for DP-SGD against Record-level Inference

Paper • 2402.14397 • Published Feb 22, 2024

Analyzing Leakage of Personally Identifiable Information in Language Models

Paper • 2302.00539 • Published Feb 1, 2023

Securing AI Agents with Information-Flow Control

Paper • 2505.23643 • Published May 29, 2025 • 1

updated a collection over 1 year ago

MICO Membership Inference Competition

Collection

Challenge datasets used for the Microsoft Membership Inference Competition. • 4 items • Updated Oct 21, 2024 • 3

updated a dataset over 1 year ago

szanella/MICO-DDP

Updated Oct 21, 2024 • 74

updated a collection over 1 year ago

MICO Membership Inference Competition

Collection

Challenge datasets used for the Microsoft Membership Inference Competition. • 4 items • Updated Oct 21, 2024 • 3

updated a dataset over 1 year ago

szanella/MICO-SST2

Updated Oct 21, 2024 • 63

upvoted a collection over 1 year ago

MICO Membership Inference Competition

Collection

Challenge datasets used for the Microsoft Membership Inference Competition. • 4 items • Updated Oct 21, 2024 • 3

updated a collection over 1 year ago

MICO Membership Inference Competition

Collection

Challenge datasets used for the Microsoft Membership Inference Competition. • 4 items • Updated Oct 21, 2024 • 3

updated 2 datasets over 1 year ago

szanella/MICO-purchase100

Updated Oct 21, 2024 • 206

szanella/MICO-CIFAR10

Updated Oct 21, 2024 • 155

authored 5 papers over 1 year ago

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

Paper • 2212.10986 • Published Dec 21, 2022

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Paper • 2406.07954 • Published Jun 12, 2024 • 2

Analyzing Information Leakage of Updates to Natural Language Models

Paper • 1912.07942 • Published Dec 17, 2019

Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective

Paper • 2311.15792 • Published Nov 27, 2023

On the Efficacy of Differentially Private Few-shot Image Classification

Paper • 2302.01190 • Published Feb 2, 2023