collaborators

5 papers

cs.CR2026

Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?

Víctor Mayoral-Vilches, Francesco Balassone, María Sanz-Gómez +5

What is the best harness for cybersecurity AI? Cybersecurity systems are converging on a single execution scaffold per agent, an iterative shell loop driven by a Large Language Mod…

cs.CR2026

Security Incentivization: An Empirical Study of how Micropayments Impact Code Security

Stefan Rass, Martin Pinzger, Rainer W. Alexandrowicz +5

Security often receives insufficient developer attention because it does not directly generate visible value, leading to underinvestment in practice. We evaluate a countermeasure b…

cs.CR2026

Towards Cybersecurity Superintelligence: from AI-guided humans to human-guided AI

Víctor Mayoral-Vilches, Stefan Rass, Martin Pinzger +14

Cybersecurity superintelligence -- artificial intelligence exceeding the best human capability in both speed and strategic reasoning -- represents the next frontier in security. Th…

cs.CR2025

Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs

Francesco Balassone, Víctor Mayoral-Vilches, Stefan Rass +4

We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI (Cybersecurity AI)'s parallel execution framework, we deployed a…

cs.CR2025

CAI: An Open, Bug Bounty-Ready Cybersecurity AI

Víctor Mayoral-Vilches, Luis Javier Navarrete-Lozano, María Sanz-Gómez +10

By 2028 most cybersecurity actions will be autonomous, with humans teleoperating. We present the first classification of autonomy levels in cybersecurity and introduce Cybersecurit…