The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision

Summary

The paper introduces SADDER, an extension of the Safety-Aware Denoiser (SAD) for text diffusion models. SADDER uses an embedding-space safety signal to gate which token positions SAD's update rule modifies, and derives new position-wise target distributions so the modified denoiser stays exact. Tested on Masked Diffusion Language Models and Uniform-State Diffusion Models in unsafe continuation and jailbreak settings, it reportedly balances safety, generation quality and inference cost better than existing methods.

Related items

• InfoDeveloping Gemini 4 Argon responsibly and safelySimilar attack · DeepMind Safety Research
• InfoRethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget SelectionSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoTop GenAI security resources — October 2026Similar attack · Adversa AI Blog
• InfoSame Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety ClassifiersSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoTRAP: Tree-Guided Reinforcement-Augmented Probing for Automated LLM JailbreakingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)