Skip to content

Commit 48974de

Browse files
committed
增加SEO ATTACK、AI靶场及相关AI应用于安全的文章
1 parent 95efc65 commit 48974de

File tree

3 files changed

+17
-5
lines changed

3 files changed

+17
-5
lines changed

content/security_research/ai_security/ai_used_in_security.md

+4-1
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ keywords:
3232
- [回村三天,chatGPT教会了我如何简单逆向app并解密数据包](https://www.freebuf.com/articles/mobile/355589.html)
3333
- [如何用ChatGPT开发一个安全工具](https://www.freebuf.com/sectool/398605.html)
3434

35-
## 安全检测
35+
## 安全检测与渗透
3636
- [火出圈的ChatGPT,如何让安全检测更智能](https://www.freebuf.com/articles/network/359678.html)
3737
- [利用深度学习检测恶意PowerShell](https://www.freebuf.com/articles/network/213619.html)
3838
- [基于机器学习的WEB攻击分类检测模型](https://www.freebuf.com/news/184687.html)
@@ -44,6 +44,9 @@ keywords:
4444
- [APOLLO:一种基于 GPT 的用于检测钓鱼邮件并生成警告用户的解释的工具](https://mp.weixin.qq.com/s/w-Rshy1GR3MZY4ca4bsrVQ)
4545
- [LLMs在供应链投毒检测中的应用](https://mp.weixin.qq.com/s/Dek0AdFNxf_C-q5pLX3ktw)
4646
- [AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?](https://arxiv.org/html/2411.01236v1)
47+
- [大模型应用实践(一):AI助力Code Review安全漏洞发现](https://mp.weixin.qq.com/s/Za2fTJBFA136v9m4I2f6UA)
48+
- [DataCon晚自习:浅谈大模型辅助漏洞挖掘](https://mp.weixin.qq.com/s/jSeA2Qu6X6cGHGEMCtkadw)
49+
- [利用AI进行渗透测试的攻击面](https://mp.weixin.qq.com/s/gLYAK2RsryckgF-DbhRozg)
4750

4851
## 安全运营与响应
4952
- [智能驱动|ChatGPT视角下的告警事件闭环响应](https://www.freebuf.com/articles/network/396552.html)

content/security_research/ai_security/llm_security/attack.md

+11-4
Original file line numberDiff line numberDiff line change
@@ -41,6 +41,7 @@ keywords:
4141
- [SuperCLUE-Safety:中文大模型多轮对抗安全基准](https://www.cluebenchmarks.com/superclue_safety.html)
4242

4343
## Prompt注入攻击
44+
- [AI安全 | Prompt越狱手册第一版发布](https://mp.weixin.qq.com/s/JiVHh119oHSxlXlEP__LgA)
4445
- [ChatGPT安全风险 | 基于LLMs应用的Prompt注入攻击](https://www.freebuf.com/articles/network/365585.html)
4546
- 《大语言模型(LLM)攻防实战手册》第一章:提示词注入 [概述](https://mp.weixin.qq.com/s/WKXVDOi2_uiDL9N8DnbCWA) / [直接提示词注入(越狱)](https://mp.weixin.qq.com/s/_Brmvgh5z0mgqkaeI41SBg) / [间接提示词注入](https://mp.weixin.qq.com/s/TnTeTLUvmaIz868vvDe3Gw) / [图解提示词注入](https://mp.weixin.qq.com/s/s6uEuhTl-K4fmhqZbDDS-w)
4647
- [通过命令提示注入来攻击大语言模型](https://www.freebuf.com/articles/system/369434.html)
@@ -50,16 +51,21 @@ keywords:
5051
- [大模型安全:平滑方法防御越狱攻击](https://forum.butian.net/share/3120)
5152
- [上海人工智能实验室:LLMs对话安全综述——攻击、防御与评估全解析](https://mp.weixin.qq.com/s/ioMr6iOWQ7Y0Ow7sFotMWQ)
5253

53-
## 越狱攻击
54+
## 越狱攻击/代码执行/沙箱安全
5455
- [针对ChatGPT的隐私提取攻击:多步骤越狱漏洞](https://www.freebuf.com/vuls/365393.html)
5556
- [大语言模型越狱攻击综述](https://mp.weixin.qq.com/s/wdEoAqXh6m-wsr2Al8WTJw)
57+
- [老树开新花:大模型时代的代码执行沙箱](https://mp.weixin.qq.com/s/X54d0foyBS56lGFUPyOvTw)
58+
- [[CCS 2024]中国科学院信息工程研究所:LLMSMITH——揭秘LLMs集成框架与应用中的RCE漏洞](https://mp.weixin.qq.com/s/cxVZ_8UG0SbMq_3XJee1cQ)
59+
60+
61+
## LLM SEO Attack
62+
- [大模型(ChatGPT)“语料污染”第一真实案例](https://mp.weixin.qq.com/s/1d5f9EQyV8Mk1OBV2V4DzQ)
63+
- [The "LLM SEO Attack" risk is becoming increasingly severe](https://securaize.substack.com/p/the-llm-seo-attack-risk-is-becoming)
64+
5665

5766
## 内容安全
5867
- [技术实践|大模型内容安全蓝军的道与术](https://www.freebuf.com/company-information/399393.html)
5968

60-
## 代码执行/沙箱安全
61-
- [老树开新花:大模型时代的代码执行沙箱](https://mp.weixin.qq.com/s/X54d0foyBS56lGFUPyOvTw)
62-
- [[CCS 2024]中国科学院信息工程研究所:LLMSMITH——揭秘LLMs集成框架与应用中的RCE漏洞](https://mp.weixin.qq.com/s/cxVZ_8UG0SbMq_3XJee1cQ)
6369

6470
## 模型及算法安全
6571
- [人工智能安全治理框架解读——模型算法安全风险及应对篇](https://mp.weixin.qq.com/s/1WU7ZHrVSk1QBffsXx-qaw)
@@ -76,3 +82,4 @@ keywords:
7682

7783
## 其他
7884
- [ZombAIs: From Prompt Injection to C2 with Claude Computer Use](https://embracethered.com/blog/posts/2024/claude-computer-use-c2-the-zombais-are-coming/)
85+

content/security_research/ai_security/others.md

+2
Original file line numberDiff line numberDiff line change
@@ -25,6 +25,8 @@ keywords:
2525
- [AIGC合规指南一:关键要点和算法备案实践](https://www.freebuf.com/articles/neopoints/390029.html)
2626
- [AIGC的隐私安全问题及隐私保护技术](https://www.freebuf.com/articles/web/358766.html)
2727

28+
## 靶场
29+
- [Hack into Al](https://hackingclub.trustai.sg/)
2830

2931
## 其他文章
3032
- [AI发展背后的数据安全](https://www.freebuf.com/articles/database/377991.html)

0 commit comments

Comments
 (0)