AWE

AWE: Adaptive Agenten für dynamisches Web-Penetrationstesting Akshat Singh Jaswal · Ashish Baghel Akzeptiert bei NDSS LAST-X 2026 Abstract Moderne Webanwendungen entstehen zunehmend durch KI-gestützte Entwicklung und schnelle No-Code-Deployment-Pipelines, wodurch sich die Kluft zwischen der...

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...