pith. sign in

Ahmed Asiri

Identifiers

  • name variant Ahmed Asiri 0.60 · backfill

Papers (2)

  1. Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling cs.CR · 2026 · author #5
  2. Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation cs.CR · 2026 · author #7

Mentions

  • 2605.24552 #5 · arxiv_oai · confidence 0.70 Ahmed Asiri
  • 2605.24535 #7 · arxiv_oai · confidence 0.70 Ahmed Asiri

Frequent Coauthors