TapGuard: Temperature-Calibrated Execute–Confirm–Block Routing for LLM-Powered Mobile Agents
International Journal of Mobile Applications and Technologies · 2026
DOI: 10.51137/wrp.ijmat.1051 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Mobile Applications and Technologies, 2026. Verfasst von Qi Xin. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large language model-powered mobile agents can compose messages, manage files, operate financial applications, and act on content from other applications. Binary allow-or-refuse safeguards fit this setting poorly: some requests are safe to execute, some require confirmation, and some should be blocked. TapGuard is a task-level pre-execution router combining a compact semantic encoder, temperature-scaled three-class probabilities, a fixed rule floor, and confidence-triggered confirmation. Experiments used 150 canonical MobileSafetyBench release 3 tasks and 100 paired action-hint variants under instruction-template and task-category holdout protocols. Under template holdout, TapGuard lowered severity-weighted direct-execution exposure from 35.7% for the MiniLM semantic classifier to 27.7%, while low-risk direct execution declined from 64.0% to 54.0%. The frozen-cue router achieved still lower exposure but directly executed only 18.0% of low-risk tasks. TapGuard increased severe-risk blocking relative to MiniLM without achieving the highest three-way macro-F1. Category holdout showed the same broad trade-off. Privacy, offensiveness, and image-linked cases remained difficult, and generalization to unseen injection patterns was not established. These findings support evaluating mobile safety routing through both protection and preserved automation.
Zitieren
APA
Xin, Q. (2026). TapGuard: Temperature-Calibrated Execute–Confirm–Block Routing for LLM-Powered Mobile Agents. International Journal of Mobile Applications and Technologies. https://doi.org/10.51137/wrp.ijmat.1051
Vancouver
Xin Q. TapGuard: Temperature-Calibrated Execute–Confirm–Block Routing for LLM-Powered Mobile Agents. International Journal of Mobile Applications and Technologies. 2026. doi:10.51137/wrp.ijmat.1051
BibTeX
@article{Xin2026,
author = {Xin, Qi},
title = {TapGuard: Temperature-Calibrated Execute–Confirm–Block Routing for LLM-Powered Mobile Agents},
journal = {International Journal of Mobile Applications and Technologies},
year = {2026},
doi = {10.51137/wrp.ijmat.1051}
}
EUVIMED