Skip to content

Commit 63d1286

Browse files
committed
增加内容链接:大模型安全:平滑方法防御越狱攻击
1 parent 40393e1 commit 63d1286

File tree

1 file changed

+1
-0
lines changed
  • content/security_research/ai_security/llm_security

1 file changed

+1
-0
lines changed

content/security_research/ai_security/llm_security/attack.md

+1
Original file line numberDiff line numberDiff line change
@@ -39,6 +39,7 @@ keywords:
3939
- [黑化AI,将恶意“注入”ChatGPT](https://www.freebuf.com/articles/neopoints/357855.html)
4040
- [ChatGPT安全风险 | 基于LLMs应用的Prompt注入攻击](https://www.freebuf.com/articles/network/365585.html)
4141
- [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)
4243

4344
## 敏感信息泄露攻击
4445
- [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

Comments
 (0)