热点
"间接提示注入" 相关文章
CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
cs.AI updates on arXiv.org 2025-10-13T04:13:27.000000Z
CommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
cs.AI updates on arXiv.org 2025-10-13T04:13:27.000000Z
Salesforce 修复严重 ForcedLeak 漏洞
HackerNews 2025-09-26T14:51:06.000000Z
Notion 3.0 AI Agents恐遭間接提示注入攻擊洩露機敏資料
AI & Big Data 2025-09-23T02:10:11.000000Z
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
cs.AI updates on arXiv.org 2025-08-22T04:02:37.000000Z
安全警报：黑客可利用谷歌日历操控智能家居
HackerNews 2025-08-08T01:50:23.000000Z
Securing Amazon Bedrock Agents: A guide to safeguarding against indirect prompt injections
AWS Machine Learning Blog 2025-05-13T17:35:56.000000Z