Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines

ArXi:2604.23483v1 Announce Type: new Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient access, and strict query budgets. We formalize this strict black-box threat model and propose a two-agent evasion framework operating in a semantic perturbation space.