Problem
Research questions and friction points this paper is trying to address.
Mobile Agents
MFA Automation
Factor Collapse
Authentication
WiP: Characterizing and Defending Against Mobile-Agent-Driven MFA Automation
🤖 AI Summary
研究解决了移动代理导致的多因素认证（MFA）自动化问题，通过开发一种基于动作识别的风险信号来区分人类和代理驱动的登录。
📝 Abstract
Mobile agents automate smartphone tasks by interpreting interfaces, interacting with apps, and coordinating cross-app workflows. This capability challenges the human-mediated separation assumed by passcode-based MFA, creating factor collapse: valid authentication factors are combined within one autonomous environment. Our modular pipeline com- pletes all 10 authorized MFA workflows, compared with 3/10 and 6/10 for two single-agent baselines. We also de- velop a motion-based Android risk signal that distinguishes human- from agent-driven logins with 98.4% table-top and 92.6% hand-held accuracy across 116 pilot sessions. These results demonstrate factor collapse and motivate physical- interaction sensing as complementary evidence of user pres- ence.
Innovation
Methods, ideas, or system contributions that make the work stand out.
mobile-agent-driven MFA
motion-based risk signal
factor collapse
🔎 Similar Papers
