Sebastian Szyller
@sebszyller.com
Assistant Professor @csaalto.bsky.social
Trustworthy & Adversarial Machine Learning
sebszyller.com & taclab.aalto.fi
Trustworthy & Adversarial Machine Learning
sebszyller.com & taclab.aalto.fi
Reposted by Sebastian Szyller
For context: the policy is now official. bsky.app/profile/ange...
blog.arxiv.org/2025/10/31/a...
FYI the blog post for the updated policy is out. Our llm future is dire:/
FYI the blog post for the updated policy is out. Our llm future is dire:/
October 31, 2025 at 8:18 PM
For context: the policy is now official. bsky.app/profile/ange...
E.g., domains that may, by regulation, require fair and private models?
April 11, 2025 at 7:35 AM
E.g., domains that may, by regulation, require fair and private models?
One notable example is differential privacy vs fairness.
Perhaps technical stakeholders can prioritise one over the other; but what if the requirement is external?
Perhaps technical stakeholders can prioritise one over the other; but what if the requirement is external?
April 11, 2025 at 7:33 AM
One notable example is differential privacy vs fairness.
Perhaps technical stakeholders can prioritise one over the other; but what if the requirement is external?
Perhaps technical stakeholders can prioritise one over the other; but what if the requirement is external?
Requirements in trustworthy ML can be contradictory — require or exploit opposite properties of models.
April 11, 2025 at 7:31 AM
Requirements in trustworthy ML can be contradictory — require or exploit opposite properties of models.
People conflate open source with “open weights” all the time. Shameless plug: sebszyller.com/blog/2024/op...
sebszyller.com
sebszyller.com
January 29, 2025 at 12:01 PM
People conflate open source with “open weights” all the time. Shameless plug: sebszyller.com/blog/2024/op...