defense arXiv Jan 22, 2026 · 10w ago
Joan Vendrell Farreny, Martí Jordà Roca, Miquel Cornudella Gaya et al. · NeuralTrust
Proposes a unified LLM security enforcement layer analogous to WAF, covering prompt injection, jailbreaks, and agent tool abuse
Prompt Injection Insecure Plugin Design nlp
This paper introduces the Generative Application Firewall (GAF), a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifies them into a single enforcement point, much like a WAF coordinates defenses for web traffic, while also covering autonomous agents and their tool interactions.
llm NeuralTrust
ML Security Papers