Purple Llama CyberSecEval: A benchmark for evaluating the cybersecurity risks of large language models | Research - AI at Meta - discu.eu

Linking pages

Recent papers / work on AI and hacking | Timothee Chauvin https://tchauvin.com/recent-papers-ai-hacking 2 comments
GitHub - tldrsec/prompt-injection-defenses: Every practical and proposed defense against prompt injection. https://github.com/tldrsec/prompt-injection-defenses 0 comments

Related searches:

Search whole site: site:ai.meta.com

Search title: Purple Llama CyberSecEval: A benchmark for evaluating the cybersecurity risks of large language models | Research - AI at Meta

See how to search.

Submit link to: