A sweeping new security study has exposed a critical and largely unaddressed vulnerability class in the iOS app ecosystem: 64% of LLM-integrated applications actively leak API credentials over the network, allowing attackers to hijack paid AI inference. A team from Wake Forest University conducted the first in-depth empirical study targeting LLM API credential leakage in iOS […]
The post AI-Powered iOS Applications Expose LLM API Credentials Through Network Traffic appeared first on Cyber Security News.