Skip to content

Author

Mohammad Mosafer

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility

Output-only safety monitoring sees only the end of a model's computation, yet the model computes its answer before emitting it: what it is internally poised to say is safety-critical. Jacobian-space (J-space) readouts, linear maps from hidden states to the output vocabulary via the model's input-output Jacobian, have b...

Mohammad Mosafer · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.