News & Updates

• The Call for Papers has been updated with further clarifications (see what changed). (Sep 9, 2026)
• The submission site is now open, and the Call for Papers has been updated with some clarifications (see what changed). (Sep 4, 2026)
• The full Call for Papers is now available. (Aug 24, 2026)
• The Call for Workshops and the Call for Competitions are now available. (Jul 22, 2026)
• The website for SaTML 2027 is now online! (Jun 29, 2026)

Interested in reviewing for SaTML 2027? We may further expand the Program Committee, also depending on the volume of abstract registrations. If you have published and peer-reviewed in security, privacy and machine learning venues, let us know if you would like to be considered for the Program Committee. Junior researchers welcome; an invitation is not guaranteed.

Important dates

All deadlines are set to 11:59 PM AoE (Anywhere on Earth), which corresponds to UTC-12 time zone.

Overview

This conference will expand on the theoretical and practical understandings of vulnerabilities inherent to machine learning (ML), explores the robustness of learning algorithms and systems, and aids in developing a unified, coherent scientific community aiming to establish trustworthy machine learning. Topics of interest include (but are not limited to):

• Novel attacks on machine learning
• Novel defenses for machine learning
• Secure and safe machine learning in practice
• Verification of algorithms and systems
• Machine learning system security
• Privacy in machine learning
• Forensic analysis of machine learning
• Fairness and interpretability
• Trustworthy machine learning in cybersecurity applications
• Trustworthy data curation

We solicit research papers, systematization of knowledge papers, and position papers (see Call for Papers for details). Furthermore, we invite proposals for our competition track (see Call for Competitions for details) and workshops (see Call for Workshops for details).