OpenAI released Privacy Filter, an open-weight 1.5B-parameter MoE model for PII redaction. Here's what it detects, how it compares, and where it fits in a real pipeline.
Ben @ Grepture
Read moreMCP gives AI agents access to your tools and data. Here's how to monitor, inspect, and block malicious MCP traffic at the gateway layer.
SecurityCompare the best open source models for PII detection and redaction in AI pipelines — GLiNER, DeBERTa, Piiranha, StarPII, and more.
SecurityDirect prompt injection is obvious — a user types something malicious. Indirect injection is invisible: poisoned documents, emails, and web pages that hijack your AI when it reads them. Here's how it works, real incidents, and how to defend against it.
Security