Large Language Models (LLMs) are increasingly embedded in child-facing contexts such as education, companionship, creative tools, but their deployment raises safety, privacy, developmental, and security risks. We conduct a systematic literature review of child-LLM interaction risks and organize findings into a structured map that separates (i) parent-reported concerns, (ii) empirically documented harms, and (iii) gaps between perceived and observed risk. Moving beyond descriptive listing, we compare how different evidence streams in surveys, incident reports, youth interaction logs, and governance guidance operationalize "harm," where they conflict, and what mitigations they imply. Based on this synthesis, we propose a protection framework that couples child-specific content safety and developmental sensitivity with security-grade controls for adversarial misuse, including prompt injection and multimodal jailbreak pathways. The framework specifies measurable evaluation targets (e.g., harmful-content avoidance, age-calibrated readability, bias parity checks, prompt-injection robustness, and monitoring transparency) to support developers, educators, and policymakers in assessing and improving child-safe LLM deployments.

翻译：大语言模型正日益嵌入面向儿童的应用场景，如教育、陪伴、创意工具等领域，但其部署引发了安全、隐私、发展和安全风险。我们通过系统性文献综述梳理了儿童-大语言模型交互风险，并将研究发现整合为结构化图谱，区分了（i）家长报告的担忧，（ii）实证记录的有害影响，以及（iii）感知风险与实测风险之间的差距。超越描述性列举，我们对比了调查数据、事件报告、青少年交互日志及治理指南中不同证据流如何界定"危害"、其间的矛盾点以及各自暗示的缓解措施。基于此综合研究，我们提出一个保护框架，该框架将针对儿童的内容安全与发展敏感性，与对抗性滥用（包括提示注入和多模态越狱路径）的安全级控制相结合。该框架明确了可量化的评估目标（例如：有害内容规避、年龄校准的可读性、偏见对等性检查、提示注入鲁棒性及监控透明度），以支持开发者、教育工作者和政策制定者评估并改进面向儿童的大语言模型部署。