CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents
Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to step away from supervision. However, this capability also exposes sensitive information to phishing. Safe execution requires distinguishing malicious...
Rafid Ahmed, Joseph Fioresi, Mubarak Shah et al.
· 0 citations