AI RESEARCH
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
arXiv CS.CL
•
ArXi:2604.18248v1 Announce Type: cross Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer classifiers. Both share failure modes that recent work has made concrete. Regular expressions miss paraphrased attacks. Fine-tuned classifiers are vulnerable to adaptive adversaries: a 2025 NAACL Findings study reported that eight published indirect-injection defenses were bypassed with greater than fifty percent attack success rates under adaptive attacks.