Meta Open Sources LlamaFirewall for AI Agent Combined Protection
LlamaFirewall is a security framework aimed at safeguarding AI agents against prompt injection, goal misalignment, and insecure code generation. It achieved over 90% efficacy in reducing attack success rates when evaluated on the AgentDojo benchmark. Additionally, developers can update its behavior by adding new security guardrails.
Llama 4 Scout and Maverick Now Available on Amazon Bedrock and SageMaker JumpStart
AWS recently announced the availability of Meta’s latest foundation models, Llama 4 Scout and Llama 4 Maverick, in Amazon Bedrock and AWS SageMaker JumpStart. Both models provide multimodal capabilities and follow the mixture-of-experts architecture.
Google Releases LMEval, an Open-Source Cross-Provider LLM Evaluation Tool
LMEval aims to help AI researchers and developers compare the performance of different large language models. Designed to be accurate, multimodal, and easy to use, LMEval has already been used to evaluate major models in terms of safety and security.
Introducing ANS: DNS-Inspired Secure Discovery for AI Agents
The Open Worldwide Application Security Project (OWASP) has recently introduced a new standard for securely discovering AI agents. Inspired by DNS, the Agent Name Service (ANS) provides a protocol-agnostic registry mechanism that uses Public Key Infrastructure (PKI) to establish agent identity and trust.