Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

ConceptJailbreak / 越狱 / 提示词越狱

越狱攻击

针对AI系统安全护栏的绕过技术，包括角色扮演注入、提示词注入攻击、对抗性后缀、语义替换等手法，旨在使AI生成被安全机制限制的内容

Source Articles

LLM红队测试：一次性快照还是持续对抗？完整指南Jul 17 Claude Mythos预览版漏洞激增：大模型安全性如何保障？Jul 12 AI安全护栏的边界：一个提示词引发的深层思考Jul 12

Overview

Mentions: 3
Facts: 0
Related Entities: 0
Type: Concept

Citation

URI

/knowledge/Jailbreak

API

/api/v1/knowledge/entity/Jailbreak

MCP

get_entity("Jailbreak")