ELSA Benchmarks Platform

Welcome to the The ELSA Benchmarks Platform! The platform provides a single access point to all ELSA Use Case related resources (data, metrics, benchmarks) and allows participation to the ELSA competitions.

Please browse the Use Cases, and find out about related events (competitions, workshops, tutorials) running. Each competition will host one or more scientific competitions over the duration of the ELSA project. Register in the platform in order to get access to download materials and to submit your own methods to the competitions.

Ongoing Events

• SaTML 2025 Competition: Inference Attacks Against Document VQA, In conjunction with SaTML 2025, April 9-11, 2025

• ICDAR Tutorial on Private, Collaborative Learning in Document Analysis, In conjunction with ICDAR 2024, September 1st, 2024

• 2nd Workshop and Challenge on Deepfake Analysis and Detection, In conjunction with CVPR 2024, June 17th, 2024

• The Health Privacy Challenge:  In conjunction with CAMDA Conference, at ISMB/ECCB 2025,  July 23-24, 2025.

Past Events

• Large Language Model Capture-the-Flag (LLM CTF) Competition (external link) @ SaTML 2024. Participate by January 15th, 2024. [VIDEO]

• 16th ACM Workshop on Artificial Intelligence and Security, In conjunction with CCS 2023. November 30, 2023. Copenhagen, Denmark

• Competition and Workshop on Privacy Preserving Federated Learning Document VQA. In conjunction with NeurIPS 2023. December 15, 2023. New Orleans, USA

• Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world , In conjunction with ICCV 2023. October 3, 2023. Paris, France

• Workshop and Challenge on DeepFake Analysis and Detection, In conjunction with ICCV 2023. October 2-3, 2023. Paris, France

• Workshop and Challenge on Multimedia DeepFake Analysis and Detection. In conjunction with ACM MM 2023. October 29 - November 3, 2023. Ottawa, Canada

Autonomous Driving

Robust Perception

Document Intelligence

Document VQA

Media Analytics

Tackling Disinformation

Health

Privacy in Computational Healthcare

Robotics

Learning Through Human Interaction

Cybersecurity

Malware Detection

Large Language Models

LLM Capture the Flag (externally hosted)

(*) overall number of submissions including private and public ones