Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
This work presents RedHerring, which inserts certifiably safe decoys that divert verification effort from real vulnerabilities, and shows that its effectiveness does not depend on decoy secrecy.
Kai-Kai Zhang, Zi-Han Zhang, Yu-Chong Xie et al.
· 0 citations