1
Triaging Threats to Specialized Guardrails
专用护栏系统的威胁分类新框架，为AI安全防护提供系统性风险评估方法
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse re…
2
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
面向青少年的大模型安全防护新方法，基于重写机制的护栏系统，聚焦内容安全与风险管控。
arXiv:2605.21609v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating i…
3
SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
企业级LLM安全防护方案，双向过滤敏感数据与违规输出，为AI应用筑牢隐私与伦理防火墙。
arXiv:2601.06366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are transforming enterprise workflows but introduce security an…