Archives

Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders

Extending the Heilmeier Catechism to Evaluate Security and Privacy Systems: Who is Left Out?

“You Have to Ignore the Dangers”: User Perceptions of the Security and Privacy Benefits of WhatsApp Mods

Unencrypted Flying Objects: Security Lessons from University Small Satellite Developers and Their Code

Talent or Luck? Evaluating Attribution Bias in Large Language Models

VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

“We’re utterly ill-prepared to deal with something like this”: Teachers’ Perspectives on Student Generation of Synthetic Nonconsensual Explicit Imagery

To reveal or conceal: Privacy and marginalization in avatars

User comprehension and comfort with eye-tracking and hand-tracking permissions in augmented reality