Paper

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content

Unreadunread

AI summary

arXiv:2605. 28116v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from user-generated content.

Reading status

Priority

About this paper

Authors: Ruoqi Guo, Yi Liu, Gelei Deng, Yiheng Xiong, Yuekang Li, Ying Zhang, Leo Yu Zhang, Lida Zhao, Ji Jie, Yuxiao Lu
Released: 2026-05-28 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, text, distributional, eval, line, rate, control, without. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2605.28116

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.