The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model — Study Protocol and Pilot

A language-model agent can refuse a malicious payment on its own, then submit the same payment when one instruction tells it to defer. We call the difference between what an agent refuses unprompted and what it submits under an explicit deference instruction the deference gap. In a published pilot, Grok (grok-4.7) refused both an unlimited token approval and an addresspoisoning invoice when acting on its own. With one added rule (“the gate decides, not you”), it submitted all three inbox items, including both attacks. A deterministic transaction gate (srariskgate 0.18.0) returned APPROVE for the legitimate invoice, HOLD for the unlimited approval, and REJECT for the look-alike recipient. This document registers the protocol for a full study before any data is collected. The study will run 5 models from 5 developers under 3 operator conditions, with 8 inbox items and 30 trials per condition (450 agent runs). It will measure each model’s refusal rate with and without a deference instruction, the resulting gap, and whether the gate’s verdicts stay the same across conditions. The analysis code is fixed and published with this record. Results will be published as version 2 of this record.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24239917
Primary Topic
Adversarial Robustness in Machine Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model — Study Protocol and Pilot

Sriram Ramakrishnan
Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
preprint

The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model — Study Protocol and Pilot

Sriram Ramakrishnan
preprint en

Abstract

A language-model agent can refuse a malicious payment on its own, then submit the same payment when one instruction tells it to defer. We call the difference between what an agent refuses unprompted and what it submits under an explicit deference instruction the deference gap. In a published pilot, Grok (grok-4.7) refused both an unlimited token approval and an addresspoisoning invoice when acting on its own. With one added rule (“the gate decides, not you”), it submitted all three inbox items, including both attacks. A deterministic transaction gate (srariskgate 0.18.0) returned APPROVE for the legitimate invoice, HOLD for the unlimited approval, and REJECT for the look-alike recipient. This document registers the protocol for a full study before any data is collected. The study will run 5 models from 5 developers under 3 operator conditions, with 8 inbox items and 30 trials per condition (450 agent runs). It will measure each model’s refusal rate with and without a deference instruction, the resulting gap, and whether the gate’s verdicts stay the same across conditions. The analysis code is fixed and published with this record. Results will be published as version 2 of this record.

Zenodo (CERN European Organization for Nuclear Research)
Adversarial Robustness in Machine Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
The Deference Gap: Why Payment-Agent Safety Must Live Outside the Model — Study Protocol and Pilot — Sriram Ramakrishnan · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS