# New Jailbreak Uses Dual-Layer Encoding to Reconstruct Blocked Prompts Past Moderation

The RoguePrompt method encodes a disallowed request so the model itself rebuilds it during generation, bypassing the moderation layer meant to catch it.

- Published: 2026-07-31T05:48:01.029Z
- Canonical: https://polylog.news/ai/2026-07-31/new-jailbreak-uses-dual-layer-encoding-to-reconstruct-blocke
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv (cs.CR)](https://arxiv.org/abs/2607.27373)

A security preprint describes a prompt-based attack that targets the gap between what a moderation filter sees and what a model reconstructs. RoguePrompt uses a dual-layer encoding for self-reconstruction. The input is encoded so that safet…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-31/new-jailbreak-uses-dual-layer-encoding-to-reconstruct-blocke (subscription information: https://polylog.news/pricing).