8 papers
Auditing AI Investment Recommendations as Executable Actions
Sidnei Barbieri, Wellington Vargas, Ãgney Lopes Roth Ferraz
AI systems increasingly produce investment recommendations, yet the usual evaluations ask the wrong question. Realized return is noisy and easy to overfit, and agreement with a ref…
From Production SIEM to Reusable Cybersecurity Artifacts
Sidnei Barbieri, Leonardo Vaz de Meneses, Ãgney Lopes Roth Ferraz +2
Operational evidence is not automatically scientific evidence. The most realistic Security Operations Center (SOC) data is production telemetry, yet it remains scientifically inacc…
ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense
Sidnei Barbieri, Ãgney Lopes Roth Ferraz, Wagner Comin Sonaglio +3
Operational evidence is not automatically scientific evidence. The most realistic Security Operations Center (SOC) data is production telemetry, yet it remains scientifically inacc…
TopVenues: A Reproducible Corpus and Tooling Substrate for Cybersecurity Literature Reviews
Sidnei Barbieri, Ãgney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior
Cybersecurity literature reviews require a reproducible denominator: the set of papers that a protocol includes before screening and synthesis begin. Today, that denominator is oft…
AutoSUT: The Environment Semantics Gap in Structured CTI for Adversary Emulation
Sidnei Barbieri, Ãgney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior
Structured Cyber Threat Intelligence (CTI) increasingly supports adversary emulation, detection evaluation, and cyber range design, yet each workflow still requires a target System…
PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents
Sidnei Barbieri, Ãgney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior
Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may ch…