SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models
"威胁模型" 相关文章
国内安全厂商应对大模型新风险的主要措施
RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
Survey of Multi-agent LLM Evaluations
Microsoft Presents a Comprehensive Framework for Securing Generative AI Systems Using Lessons from Red Teaming 100 Generative AI Products
GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
Model evals for dangerous capabilities
Auto-Enhance: Developing a meta-benchmark to measure LLM agents’ ability to improve other agents
Risk Overview of AI in Bio Research
