Llama Firewall: Comprehensive Guardrails for LLM Applications
A brief on Llama Firewall from Meta, a comprehensive system of guardrails for securing LLM applications and agents.
Topic
Security
A collection of posts on security.
Content Safety with Llama Guard and Groq
A brief on content safety (according to MLCommons taxonomy) using Meta Llama Guard and Groq Cloud.
CSA AI Controls Matrix: A Sneak Preview
A sneak preview into CSA AI Controls Matrix, the latest framework addressing AI security needs.
ICANN Sunsets WHOIS: What Does This Mean For You?
A brief on the recent announcement from ICANN to sunset WHOIS in favour of RDAP.
LLM Safety and Security with Google Cloud Model Armor
A brief on Google Cloud Model Armor, a fully managed service for the safety and security of LLM applications.
OWASP Non-Human Identities (NHI) Top 10 Risks
A gist of the latest OWASP Non-Human Identities (NHI) Top 10 risks.
Detect Jailbreaks and Prompt Injections with Meta Prompt Guard
A brief on detecting prompt attacks like injection and jailbreaks using Meta Prompt Guard.
Protect Jupyter Notebooks with NB Defense Extension
A step-by-step guide on protecting Jupyter notebooks with NB Defense, an open-source extension by Protect AI.
From Passwords to Passkeys: 5 Things to Watch Out
A brief on the considerations and potential caveats for widespread passkey adoption.
SANS: 5 Most Dangerous New Attacks in 2024
A gist of the latest SANS briefing on 5 most dangerous new attacks in 2024.