Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

Computer Science > Cryptography and Security [Submitted on 29 May 2026] Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense Shuhao Zhang, Jiarui Li, Qi Cao, Ruiyi Zhang, Pengtao Xie Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed single-detector pipeline, committing every request to one detector's blind spots. We reframe defense as detector allocation: given a heterogeneous pool, decide per request which detectors to run and whether to escalate to an LLM judge. Our framework SCOUT (Scalable and Controllable Outcome-prediction for Uncertainty-aware Triage) makes this decision dynamic by predicting each detector's per-sample reliability and latency from how it behaved on similar past inputs, and exposes a single safety-utility threshold to the operator (where utility bundles benign-pass rate and wall-clock). To evaluate this setting, we build SCOUT-450, a benchmark that captures the structurally complex, agent-facing injections that older prompt-injection sets under-represent. On SCOUT-450, a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge, at a 5.1-point benign-utility drop. SCOUT also transfers to three external benchmarks (BIPIA, IPI, and IHEval), improving the safety-utility frontier. Comments: We propose SCOUT, a detector allocation framework that predicts each detector's accuracy and latency on a given input before running it, letting operators control the safety-utility trade-off with a single threshold and route to an LLM judge only when needed Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2605.30837 [cs.CR]   (or arXiv:2605.30837v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.30837 Focus to learn more Submission history From: Shuhao Zhang [view email] [v1] Fri, 29 May 2026 04:49:20 UTC (21,540 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)