Call for Papers
|Author notification||March 26, 2021 Anywhere on Earth (AoE)|
|Camera ready deadline||April 30, 2021 Anywhere on Earth (AoE)|
|Submission format||Submissions need to be anonymized, and use the latex template here, modified from the template for ICLR conference papers. Submissions should include at most 4 pages, excluding the references and appendices.|
We invite submissions on any aspect of ML security and safety. Topics include but are not limited to:
- Adversarial attacks against ML systems, including training and test time attacks
- Improving model robustness against attacks, including empirical and certifiable defenses
- Theoretical understanding of adversarial machine learning
- AI safety for real-world deployment
- Formal verification of machine learning systems
- Explainable and interpretable AI
- Futuristic concerns about AI safety
We only consider submissions that haven’t been published in any peer-reviewed venue, including ICLR 2021 conference. The workshop is non-archival and will not have any official proceedings. Based on the PC’s recommendation, the accepted papers will be allocated either a contributed talk or a poster presentation.
We offer a Best Paper Award ($1,000), a Best Paper Honorable Mention Award ($500), and several travel grants (complimentary ICLR conference registrations), with the funding from Open Philanthropy.