Skip to main content
Search

# Cyber deception

1 related articles

Subscribe to updates
  1. arXiv

    Safe decoys for AI vulnerability hunters: confirmed real bugs fall 38.7% to 60.4% across five models

    In autonomous vulnerability discovery, an AI agent forms hypotheses cheaply but spends most of its budget verifying them. RedHerring inserts certifiably safe decoy paths into a repository to divert that verification effort away from real vulnerabilities. Across 33 OSS-Fuzz projects, 70 evaluation instances and five models under matched budgets, confirmed real vulnerabilities fall by 38.7% to 60.4%; even when the agent is told decoys may be present, the reduction is still 37.2% relative to an informed baseline.

You’re all caught up