2 papers
cs.CR2026
Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions
Eduardo Almeida Palmieri, Mohamed Chahine Ghanem, Dipo Dunsin +3
The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cy…
cs.AI2026
Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines
Mazal Bethany, Kim-Kwang Raymond Choo, Nishant Vishwamitra +1
Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under…