attack surfaces 1autonomous agent security 1misused channel 1mobile agents 1screen perception 1vision-language models 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents
Zidong Zhang, Zhentao Xie, Wenrui Diao +1
The paper investigates new security vulnerabilities in third‑party mobile agents that use vision‑language models, identifying novel attack surfaces such as screen perception gaps a…
cs.CR2026
Mini-Programs, Mega-Problems: Unveiling OAuth-based Authentication Misuses in Mini-Programs via Dynamic Analysis
Zidong Zhang, Zhentao Xie, Lingyun Ying +4
Mini-programs have become a dominant paradigm for lightweight application deployment within super apps such as WeChat. To support seamless integration, super apps provide OAuth mec…