2 papers
cs.CR2026
Introducing the Generative Application Firewall (GAF)
Joan Vendrell Farreny, Martà Jordà Roca, Miquel Cornudella Gaya +4
This paper introduces the Generative Application Firewall (GAF), a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-…
cs.CR2026
The Echo Chamber Multi-Turn LLM Jailbreak
Ahmad Alobaid, Martà Jordà Roca, Carlos Castillo +1
The availability of Large Language Models (LLMs) has led to a new generation of powerful chatbots that can be developed at relatively low cost. As companies deploy these tools, sec…