Research
BRANCH: Bypassing Multi-Scanner AI Guardrails
Publication date unknown · Discovered arxiv.org
Page published
Publication date unknown · First observed: 19 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
BRANCH’s reported transferability highlights the need for defenders to test scanner ensembles jointly rather than assume that combining detectors prevents prompt-injection and jailbreak bypasses.
BRANCH is a research methodology that uses branching tree search and scanner-specific adversarial perturbations to bypass multi-scanner AI guardrails while preserving prompt meaning. The authors report 100% attack success across six guardrail systems in 120 scenarios, with 72% fewer queries than comparison techniques, and demonstrate transfer to 29 unseen guardrails, including eight commercial black-box systems.