From fddc1e8aad13f359196dbaa371cc09ffac685a38 Mon Sep 17 00:00:00 2001 From: Apurv Verma Date: Sun, 20 Oct 2024 12:52:02 -0400 Subject: [PATCH 1/4] Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. --- readme.md | 1 + 1 file changed, 1 insertion(+) diff --git a/readme.md b/readme.md index baed0403eb..65fe8e9b57 100644 --- a/readme.md +++ b/readme.md @@ -643,6 +643,7 @@ - [Suricata](https://github.com/satta/awesome-suricata#readme) - Intrusion detection/prevention system and network security monitoring engine. - [Prompt Injection](https://github.com/FonduAI/awesome-prompt-injection#readme) - A type of vulnerability that specifically targets machine learning models. - [Detection Engineering](https://github.com/infosecB/awesome-detection-engineering#readme) - Design, build, and operate detective cybersecurity controls. +- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms) - Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. ## Content Management Systems From 0504490f1e103cf4ada2f5c65fe5a527e179648b Mon Sep 17 00:00:00 2001 From: Apurv Verma Date: Mon, 11 Nov 2024 22:08:06 -0800 Subject: [PATCH 2/4] Update readme.md Co-authored-by: Isabela de Matos <30164700+idematos@users.noreply.github.com> --- readme.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/readme.md b/readme.md index 65fe8e9b57..29a031be99 100644 --- a/readme.md +++ b/readme.md @@ -643,7 +643,7 @@ - [Suricata](https://github.com/satta/awesome-suricata#readme) - Intrusion detection/prevention system and network security monitoring engine. - [Prompt Injection](https://github.com/FonduAI/awesome-prompt-injection#readme) - A type of vulnerability that specifically targets machine learning models. - [Detection Engineering](https://github.com/infosecB/awesome-detection-engineering#readme) - Design, build, and operate detective cybersecurity controls. -- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms) - Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. +- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms#readme) - Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. ## Content Management Systems From dbf70edfed57f4e0250ef7609b60bc4c0e752e95 Mon Sep 17 00:00:00 2001 From: Apurv Verma Date: Tue, 12 Nov 2024 12:13:19 -0500 Subject: [PATCH 3/4] Fixed lint issues and changed text --- readme.md | 1 + 1 file changed, 1 insertion(+) diff --git a/readme.md b/readme.md index 29a031be99..7486e8b6c0 100644 --- a/readme.md +++ b/readme.md @@ -644,6 +644,7 @@ - [Prompt Injection](https://github.com/FonduAI/awesome-prompt-injection#readme) - A type of vulnerability that specifically targets machine learning models. - [Detection Engineering](https://github.com/infosecB/awesome-detection-engineering#readme) - Design, build, and operate detective cybersecurity controls. - [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms#readme) - Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. +- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms) - Systematizing Large Language Model Security: Attack Taxonomy, Defense Framework, and Red-Teaming Protocols ## Content Management Systems From 9595dc8452abce4c3993635115734cb233d38c46 Mon Sep 17 00:00:00 2001 From: Apurv Verma Date: Tue, 12 Nov 2024 12:15:38 -0500 Subject: [PATCH 4/4] Append readme at the end --- readme.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/readme.md b/readme.md index 7486e8b6c0..c76402a445 100644 --- a/readme.md +++ b/readme.md @@ -643,8 +643,7 @@ - [Suricata](https://github.com/satta/awesome-suricata#readme) - Intrusion detection/prevention system and network security monitoring engine. - [Prompt Injection](https://github.com/FonduAI/awesome-prompt-injection#readme) - A type of vulnerability that specifically targets machine learning models. - [Detection Engineering](https://github.com/infosecB/awesome-detection-engineering#readme) - Design, build, and operate detective cybersecurity controls. -- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms#readme) - Systematizing LLM security: A threat model for red-teaming attacks and defense strategies. -- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms) - Systematizing Large Language Model Security: Attack Taxonomy, Defense Framework, and Red-Teaming Protocols +- [Red-Teaming LLMs](https://github.com/dapurv5/awesome-red-teaming-llms#readme) - Systematizing Large Language Model Security: Attack Taxonomy, Defense Framework, and Red-Teaming Protocols ## Content Management Systems