Metraipolis › archive › dc_735dd712005c

FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models — arXiv:2610.38895

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.38895
License (as archived): CC0-1.0
Archived: 2026-10-31T06:12:57.637Z
SHA-256 of the archived text: 20f58967acde2ac882c1f49d298cf669d5c50004240ac2e9c4af988d64444fb8
Stable URL of this page: https://metraipolis.com/documento/dc_735dd712005c

How to cite

FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models — arXiv:2610.38895 — arXiv (en), https://arxiv.org/abs/2610.38895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_735dd712005c (Metraipolis archive dc_735dd712005c, sha256 20f58967acde2ac882c1f49d298cf669d5c50004240ac2e9c4af988d64444fb8)

BibTeX

@misc{dc735dd712005c,
  title = {FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models — arXiv:2610.38895},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38895},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_735dd712005c; sha256 20f58967acde2ac882c1f49d298cf669d5c50004240ac2e9c4af988d64444fb8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Typed decision models are an emerging class of language models that make decisions instead of generating free-text responses. They answer in a single fast and cheap query and are increasingly used, including in security-sensitive tasks. However, red teaming of these models leaves two gaps: existing adaptive attacks do not use their speed, and few studies have searched for universal adversarial examples. We fill both gaps on Jev, the representative typed decision model, with a quick black-box query-based attack that calls no attacker language model. We conduct extensive experiments on 12 datasets with different data types and application scenarios. The results show that Jev resists common prompt injections: no strategy changes a correct answer in 10,240 paired tests. In contrast, our attack finds short suffixes that flip confident answers within minutes. These suffixes are universal: one suffix per dataset flips 43% of unseen documents. Because typed decision models, unlike classic NLP models, can serve many tasks, we test whether these suffixes transfer across tasks. We find that one suffix generated from one task can flip 90-100% of the samples in other tasks. We therefore believe the evaluation of typed decision models must include strict adaptive attacks to fully reveal their robustness.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.38895 — 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 2026-10-31T06:07:08.681Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).