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

TL;DR

This paper reviews recent advances in AI-driven cybersecurity, highlighting three key developments that demonstrate AI surpassing human capabilities in speed, reasoning, and strategic decision-making, paving the way for superintelligence in security.

Contribution

It introduces three pioneering systems—PentestGPT, Cybersecurity AI, and G-CTR—that collectively demonstrate AI's progression towards superintelligence in cybersecurity tasks.

Findings

PentestGPT improves penetration testing efficiency by 228.6%.

Cybersecurity AI operates 3,600x faster than humans and reduces costs significantly.

G-CTR doubles success rates and enhances strategic reasoning in attack and defense scenarios.

Abstract

Cybersecurity superintelligence -- artificial intelligence exceeding the best human capability in both speed and strategic reasoning -- represents the next frontier in security. This paper documents the emergence of such capability through three major contributions that have pioneered the field of AI Security. First, PentestGPT (2023) established LLM-guided penetration testing, achieving 228.6% improvement over baseline models through an architecture that externalizes security expertise into natural language guidance. Second, Cybersecurity AI (CAI, 2025) demonstrated automated expert-level performance, operating 3,600x faster than humans while reducing costs 156-fold, validated through #1 rankings at international competitions including the $50,000 Neurogrid CTF prize. Third, Generative Cut-the-Rope (G-CTR, 2026) introduces a neurosymbolic architecture embedding game-theoretic reasoning into LLM-based agents: symbolic equilibrium computation augments neural inference, doubling success rates while reducing behavioral variance 5.2x and achieving 2:1 advantage over non-strategic AI in Attack & Defense scenarios. Together, these advances establish a clear progression from AI-guided humans to human-guided game-theoretic cybersecurity superintelligence.