Overview
Severity: MEDIUM | Affected: Robust Intelligence | Category: tool
AI security firm Robust Intelligence has launched the second major version of its open-source 'AI Firewall.' This framework is designed to be deployed in front of AI applications to provide real-time protection against a wide range of threats. Version 2.0 introduces significant enhancements, including a dedicated module for detecting complex prompt injection and jailbreak attempts like the recently discovered 'Recursive Embedding' attack. It also adds capabilities for real-time PII redaction, denial-of-service (DoS) protection through resource consumption monitoring, and detection of model-based data exfiltration. The tool integrates directly with popular MLOps platforms and API gateways, allowing developers to easily secure their AI-powered applications without extensive code changes. The release aims to democratize access to enterprise-grade AI security measures and establish a common defense layer for the rapidly growing ecosystem.