Metraipolis › archive › dc_b3d48dedb271
Signing the Transaction but Not the Decision: Whisper Attacks and a Binding Defense for AP2 — arXiv:2609.11757
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11757
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:46:41.678Z
- SHA-256 of the archived text
5e3d164fa4c0c37c3be4bf96f910671514eccb07158b59e75a1b40b48a28cc27- Stable URL of this page
https://metraipolis.com/documento/dc_b3d48dedb271
How to cite
Signing the Transaction but Not the Decision: Whisper Attacks and a Binding Defense for AP2 — arXiv:2609.11757 — arXiv (en), https://arxiv.org/abs/2609.11757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3d48dedb271 (Metraipolis archive dc_b3d48dedb271, sha256 5e3d164fa4c0c37c3be4bf96f910671514eccb07158b59e75a1b40b48a28cc27)
BibTeX
@misc{dcb3d48dedb271,
title = {Signing the Transaction but Not the Decision: Whisper Attacks and a Binding Defense for AP2 — arXiv:2609.11757},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11757},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3d48dedb271; sha256 5e3d164fa4c0c37c3be4bf96f910671514eccb07158b59e75a1b40b48a28cc27},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Software agents are beginning to shop and pay on a person's behalf. Agent payment protocols such as AP2 produce cryptographically valid signatures for completed purchases, yet do not constrain the decisions that lead to them. Consequently, ordinary product-description text can steer a shopping agent into forming a cart that passes every protocol check but no longer matches the user's request. In this paper, we show that this vulnerability enables three related attacks. In the first attack, the agent is steered into fetching another user's payment credentials. In the second, it assembles a cryptographically valid cart whose contents do not match what the user was shown. In the third, a single factual claim about stock or product lineage moves the agent from the cheaper displayed item to a more expensive one, while the resulting cart remains fully consistent with the listing. In experiments using the Gemini Flash-Lite models that AP2's sample agents specify by default, the three attacks succeeded at rates of 90%, 56%, and 73.3%, respectively. The same vulnerability appears across seventeen Google models, three unrelated agent frameworks, two cross-vendor anchors, and Google's own consumer assistant. To address this attack vector, we introduce A-VIP (AP2 Verified-Intent Protection), a protocol-layer defense that treats the signed intent as a capability grant rather than judging the merchant's description. The defense binds every credential lookup to the session that requested it and every cart line to the listing seen, while flagging unauthorized spending. The first two attacks leave structural traces that these bindings block with zero false positives. The third attack leaves no trace, so A-VIP surfaces unauthorized spending for user confirmation. Finally, we release the A-VIP code, machine-checked invariants, and AP2-WhisperBench, a suite of 1,544 evaluation scenarios. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.11757 — 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 2026-10-16T05:30:39.401Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).