AWE

AWE: Agentes Adaptativos para Pruebas de Penetración Web Dinámicas Akshat Singh Jaswal · Ashish Baghel Aceptado en NDSS LAST-X 2026 Resumen Las aplicaciones web modernas se producen cada vez más mediante desarrollo asistido por IA y pipelines de despliegue sin código de rápida evolución, lo que...

AWE: Adaptive Agents for Dynamic Web Penetration Testing

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling. Pattern-driven scanners fail to reason about novel contexts,...

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection

Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent systems incorporate large language models LLMs, they are still prompt-based, deterministic pipelines that underutilize reasoning capability. We present...