Research
BRANCH: Bypassing Multi-Scanner AI Guardrails
Publication date unknown · Discovered arxiv.org
Page published
Publication date unknown · First observed: 13 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
BRANCH demonstrates that stacking multiple collaborative scanners does not reliably protect LLMs, since its adversarial bypasses transfer to commercial black-box guardrails with no additional optimization, undermining a common defensive strategy.
BRANCH is a research methodology by William Hackett and Peter Garraghan that bypasses multi-scanner AI guardrail systems using a branching tree-search approach that dynamically applies adversarial perturbations against individual scanners while optimizing across the whole guardrail ensemble. The authors report a 100% attack success rate across 6 guardrail systems in 120 scenarios with 72% fewer queries and 4.5x reduced runtime, and show the bypasses transfer to 29 unseen guardrails including 8 commercial black-box systems.