We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 40393e1 commit 63d1286Copy full SHA for 63d1286
content/security_research/ai_security/llm_security/attack.md
@@ -39,6 +39,7 @@ keywords:
39
- [黑化AI,将恶意“注入”ChatGPT](https://www.freebuf.com/articles/neopoints/357855.html)
40
- [ChatGPT安全风险 | 基于LLMs应用的Prompt注入攻击](https://www.freebuf.com/articles/network/365585.html)
41
- [AI安全|LLM 01 提示词注入](https://mp.weixin.qq.com/s/A4kzMFMjrbJ_cYMLMNrTMQ)
42
+- [大模型安全:平滑方法防御越狱攻击](https://forum.butian.net/share/3120)
43
44
## 敏感信息泄露攻击
45
- [针对ChatGPT的隐私提取攻击:多步骤越狱漏洞](https://www.freebuf.com/vuls/365393.html)
0 commit comments