LLM security

9 posts · 3 sources

AnthropicBlog4d

An opt-in vulnerability-finding service for open-source software

CloudflareBlog11 Mar

AI Security for Apps is now generally available

AnthropicBlog13 Jun

Cyber toolkits for LLMs

DropboxBlog18 Sept

How we use Lakera Guard to secure our LLMs

AnthropicBlog2 Apr

Many-shot jailbreaking

DropboxBlog19 Mar

Bye Bye Bye...: Evolution of repeated token attacks on ChatGPT models

CloudflareBlog4 Mar

Cloudflare announces Firewall for AI

AnthropicBlog14 Jan

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

DropboxBlog19 Jul

Don't you (forget NLP): Prompt injection with control characters in ChatGPT