Mind Your Key: An Empirical Study of LLM API Credential Leakage in IOS Apps

The rapid integration of large language models LLMs into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized access to LLM inference services, causing financial damage to developers. Prior work on credential leakage has focused...

Vulnerabilities Drop Per Site, Most Sites Remain Vulnerable

For at least the third year in a row, the number of serious vulnerabilities per website has fallen. That sounds like good news until you look at the numbers and realize that the average website carried an astonishing 56 holes in 2012, according to statistics compiled by WhiteHat Security...