{
  "id": 6613,
  "url": "https://arxiv.org/abs/2605.06669v2",
  "title": "Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs",
  "summary": "Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency. We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextu",
  "authors": "Alexandre Cristovão Maiorano",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-29T18:52:01.000Z",
  "fetched_at": "2026-07-14T16:32:37.309Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6613",
  "original_url": "https://arxiv.org/abs/2605.06669v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}