IEEE Conference on Secure and Trustworthy Machine Learning

Prior to the SaTML conference in February 2023, you are invited to participate in any of the 3 competitions that have been accepted to SaTML. Results will then be presented and discussed by participants and organizers during the conference. Please contact the organizers of the competitions directly with any questions you may have:

• Model Attribution Challenge organized by Deepesh Chaudhari, Hyrum Anderson, Keith Manville, Lily Wong, Jonathan Broadbent, Christina Liaghati, Joao Gante, Ram Shankar, Yonadav Shavit, Elizabeth Merkhofer.
• Improving training data extraction attacks on large language models organized by Nicholas Carlini, Christopher Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Milad Nasr, Florian Tramer, Chiyuan Zhang.
• MICO: A Membership Inference Competition organized by Giovanni Cherubin, Ana-Maria Cretu, Andrew Paverd, Ahmed Salem, Santiago Zanella-Beguelin.

The Winners of the MICO: A Membership Inference Competition can be found here.

Below is the final report for the ML Model Attribution Challenge that was organized along with this first edition of SaTML. To cite the report:

@techreport{merkhofer2023mlmac,
title={Machine Learning Model Attribution Challenge},
author={Elizabeth Merkhofer and Deepesh Chaudhari and Hyrum S. Anderson and Keith Manville and Lily Wong and João Gante},
institution={First IEEE Conference on Secure and Trustworthy Machine Learning, Competition Track},
year={2023},
}