Metraipolis › archive › dc_b50ab4fa4f49
Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards — arXiv:2609.26178
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26178
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:42:06.601Z
- SHA-256 of the archived text
1d23148bfd206307c16bfc5ebb936a27aaba49c887904ae765b24b6e2815d61d- Stable URL of this page
https://metraipolis.com/documento/dc_b50ab4fa4f49
How to cite
Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards — arXiv:2609.26178 — arXiv (en), https://arxiv.org/abs/2609.26178 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b50ab4fa4f49 (Metraipolis archive dc_b50ab4fa4f49, sha256 1d23148bfd206307c16bfc5ebb936a27aaba49c887904ae765b24b6e2815d61d)
BibTeX
@misc{dcb50ab4fa4f49,
title = {Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards — arXiv:2609.26178},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26178},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b50ab4fa4f49; sha256 1d23148bfd206307c16bfc5ebb936a27aaba49c887904ae765b24b6e2815d61d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26178. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When an encoded attack passes a content guard, the guard either never represented the payload's harmful content or represented it and failed to act. End-to-end attack success rate reports one number for both, yet the two have opposite remedies: one is a representational limit that more safety training cannot reach, the other is a decision rule that it can. We separate them by reading a guard's own residual stream, using a content probe fitted on plaintext and transferred without refitting to the encoded condition, alongside the verdict logits from the same pass. Licensing that read honestly is most of the problem and is our main contribution. A conventional permutation test admits the decode measurement on most of a 19-condition encoding ladder for each of two open guards. A length-matched null and a floor calibrated on conditions the guard's base model provably cannot decode reduce it to four conditions each; holding out the items the probe was fitted on removes one more. A third screen constrains the block axis, which the decode screens leave untouched, by running plaintext content inside each condition's own wrapper. It removes the largest cell that survived them. What remains is a policy failure that survives an item-level holdout on two of the four surviving conditions, at 8 and 7 per 100 prompts, against 17 and 23 when the probe is allowed to have seen the prompt it is scoring. It is also confined to one family of surface encodings: where an encoding leaves content linearly recoverable we can separate the two failures, and on genuine ciphers we report the cells as unmeasured rather than as evidence that nothing was decoded. Across every guard and condition pair, blocked without decoding is near zero, so we find little evidence for a pure encoding-format detector under the conditions we test. That cell is the one read we do not repeat under the holdout, and we report it as such. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.26178 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:55:11.745Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).