knowledge base of adversary tactics and techniques based on real-world attack observations and realistic demonstrations from AI red teams and security groups, modeled after the MITRE ATT&CK® framework.
Cross-referenced across 55 tracked directories
#3754
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
3/13/2026
First Seen
Recently added to the ecosystem
From Prompt Injection to C2 with Claude Computer Use
"key attack vectors that threat actors can exploit to compromise or manipulate LLMs".
LLM security and privacy
the Open Worldwide Application Security Project's list related to LLMs [[Youtube video]](https://www.youtube.com/watch?v=engR9tYSsug)
...more