pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CR 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

The Safety-Aware Denoiser for Text Diffusion Models

cs.LG · 2026-04-28 · unverdicted · novelty 7.0

SAD modifies the denoising process in text diffusion models to enforce safety constraints at inference time, reducing unsafe generations while preserving quality and diversity.

citing papers explorer

Showing 2 of 2 citing papers.

  • The Safety-Aware Denoiser for Text Diffusion Models cs.LG · 2026-04-28 · unverdicted · none · ref 45

    SAD modifies the denoising process in text diffusion models to enforce safety constraints at inference time, reducing unsafe generations while preserving quality and diversity.

  • Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing cs.CR · 2026-05-11 · unverdicted · none · ref 65

    DR-Smoothing introduces a disrupt-then-rectify prompt processing scheme into smoothing defenses, delivering tight theoretical bounds on success probability against both token- and prompt-level jailbreaks.