← Back to the wire

Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents

AnnouncementResearchJul 10, 2026

Yingchen Zhang and Puji Wang propose TokenWall, a runtime defense framework that audits natural-language token flows in persistent AI agents to intercept unsafe behavior before execution. Experiments on CIK-Bench show TokenWall reduces attack success rate to 12.5% while maintaining a 97.4% benign executable pass rate, adding only 0.69 seconds of latency on benign cases. The framework constructs structured source-sink audit records and applies lightweight local inspection, escalating ambiguous high-risk cases to stronger arbitration modules.

Receipt № 4731 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01medPRIMARY
Yingchen ZhangPersonPuji WangPerson
Canonical: https://arxiv.org/abs/2607.08395