Naples, IT 40.85°N 14.27°E researching

Francesco Balassone

AI Security Research Lead @ CYBER RANGES · PhD @ Federico II

Teaching machines to attack,
so we learn how to defend.

Read the research Get in touch

FIG. 00entry → lateral → contained

I'm Francesco, an AI cybersecurity researcher. I build and evaluate offensive and defensive AI agents that hack, defend and emulate real adversaries, for military, government and enterprise.

Formerly atAlias Robotics

FIG. 01 · Offensive Agent vs Defensive Agent click a machine for its logs · drag to rotate

    An Offensive Agent moves through a network from left to right; a Defensive Agent detects and contains it.

    01

    Research

    Where offensive security meets AI agents.

    Home lab

    I'm a PhD student at ARCLAB, in the Department of Electrical Engineering and Information Technology (DIETI) of the University of Naples Federico II.

    Inside ARCLAB we run DARKLAB, the lab's cybersecurity branch, working on offensive and defensive AI, adversary emulation and CTFs, a few steps from the Maradona stadium in Fuorigrotta.

    FIG. 02ARCLAB · DARKLAB, inside DIETI · Via Claudio, next to the Maradona
    FIG. 02a▲ initial-access vectors → target
    A · Offense

    Agentic offensive security

    Offensive agents that plan and execute real attack chains, ranking #1 among AI teams in security CTFs, competing in Attack/Defense battlegrounds and testing real systems, from OT networks to consumer robots.

    FIG. 02b● APT trails · ┄ synthetic copy
    B · Adversaries

    Adversary emulation & attribution

    AI agents configured as real APT groups such as APT28, APT29, APT41, APT44 and Lazarus raise a hard question: if anyone can emulate a playbook, do TTPs still tell us who attacked?

    FIG. 02c■ flags captured across the range
    C · Evaluation

    Benchmarks & cyber ranges

    Static benchmarks saturate. I work on harder yardsticks: meta-benchmarks, harness comparisons and Dynamic Cyber Ranges where LLM defenders fight back in real time.

    02

    Publications

    1. 2026
      Synthetic APTs: the Collapse of TTP-Based Attribution

      F. Balassone, V. Mayoral-Vilches, M. Sanz-Gómez, P. Zabalegui-Landa, et al.

      arXiv:2606.07158

    2. 2026
      Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?

      V. Mayoral-Vilches, F. Balassone, M. Sanz-Gómez, P. Zabalegui-Landa, et al.

      arXiv:2605.28334

    3. 2026
      Dynamic Cyber Ranges

      V. Mayoral-Vilches, M. Sanz-Gómez, F. Balassone, et al.

      arXiv:2604.24184

    4. 2026
      Cybersecurity AI: Hacking Consumer Robots in the AI Era

      V. Mayoral-Vilches, U. Ayucar-Carbajo, O. Laflamme, R. Peng, et al.

      arXiv:2603.08665

    5. 2026
      Towards Cybersecurity Superintelligence

      V. Mayoral-Vilches, S. Rass, M. Pinzger, E. Gil-Uriarte, et al.

      Proceedings of the AAAI Symposium Series 9(1)

    6. 2026
      Cybersecurity AI: A Game-Theoretic AI for Guiding Attack and Defense

      V. Mayoral-Vilches, M. Sanz-Gómez, F. Balassone, S. Rass, et al.

      arXiv:2601.05887

    7. 2025
      Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs

      F. Balassone, V. Mayoral-Vilches, S. Rass, M. Pinzger, G. Perrone, et al.

      AAAI-26 Workshop on AI for Cyber Security (AICS)

    8. 2025
      Cybersecurity AI: The World's Top AI Agent for Security Capture-the-Flag (CTF)

      V. Mayoral-Vilches, L.J. Navarrete-Lozano, F. Balassone, M. Sanz-Gómez, et al.

      arXiv:2512.02654

    9. 2025
      Cybersecurity AI in OT: Insights from an AI Top-10 Ranker in the Dragos OT CTF 2025

      V. Mayoral-Vilches, L.J. Navarrete-Lozano, F. Balassone, M. Sanz-Gómez, et al.

      arXiv:2511.05119

    10. 2025
      Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agents

      M. Sanz-Gómez, V. Mayoral-Vilches, F. Balassone, L.J. Navarrete-Lozano, et al.

      AAAI-26 Workshop on Reproducible AI (RAI)

    11. 2025
      CAI: An Open, Bug Bounty-Ready Cybersecurity AI

      V. Mayoral-Vilches, L.J. Navarrete-Lozano, M. Sanz-Gómez, L.S. Espejo, et al.

      AAAI-26 Workshop on AI for Cyber Security (AICS)

    Full list on Google Scholar ↗

    Talks

    1. 2026
      Cybersecurity AI (CAI): Teaching Machines To Pwn

      Talk and co-presented tutorial · session “The role of genAI in today and tomorrow’s cybersecurity training programs and competitions”

      ITASEC & SERICS 2026 · Joint National Conference on Cybersecurity · Cagliari, Feb 9 · recording ↗ (in Italian)

      Title slide: Cybersecurity AI (CAI), Teaching Machines to Pwn, ITASEC 2026
    03

    CTF team

    Co-founder & Captain

    The competitive hacking team of the University of Naples Federico II.

    napwnli was born in 2024 from the finalists of the Naples team of CyberChallenge.IT. I co-founded it and I captain it: we play CTFs all over the world, learn together, and build a community of people who enjoy hard problems like web, pwn, crypto, reversing and Attack/Defense.

    2024founded in Naples
    1stCyberCup.IT 2025 · Junior
    #13in Italy on CTFtime · 2026
    FIG. 04Attack/Defense round · exploits out, patches in

    PROUD TO BENAPWNLI

    04

    Blog

    All posts →

    First posts are on the way.

    05

    About

    I lead AI security research at CYBER RANGES and I'm an industrial PhD student at the University of Naples Federico II.

    At CYBER RANGES I lead AI security research, drills and training programs for military, government and law enforcement. My PhD, “Towards Autonomous Red Teaming: Agentic AI for Offensive Cybersecurity Operations”, is supervised by Profs. Simon Pietro Romano and Gaetano Perrone, in partnership with Alias Robotics and CYBER RANGES.

    Before that, at Alias Robotics, I co-created CAI and led research on agentic AI for offense and defense: from Jeopardy CTFs to full Attack/Defense competitions, synthetic APT campaigns and production-like cyber ranges.

    Before the papers there were CTFs. I co-founded and captain napwnli, and I've gone from CyberChallenge.IT student to instructor, still the best way I know to learn how systems break.

    “TL;DR I like computers. I'm not sure they like me…”
    francesco@duel0: ~
    $ neofetch
    francesco@duel0
    OS
    Napoli · 40.85°N 14.27°E
    Host
    CYBER RANGES · AI Security Research Lead
    Kernel
    PhD · DIETI, University of Naples Federico II
    Lab
    ARCLAB · DARKLAB
    Team
    napwnli · co-founder & captain
    Uptime
    hacking since CyberChallenge.IT 2021
    Packages
    11 papers · 1 talk
    Theme
    offense ↔ defense
    Shell
    bottom-right ↘

    Experience

    1. 2026now
      AI Security Research LeadCYBER RANGES
    2. 2026
      AI/ML Specialist, DFIRNATO CCDCOE · Locked Shields
    3. 2025–26
      AI Cybersecurity Researcher, Offensive SecurityAlias Robotics · started as research intern
    4. 2024now
      Co-Founder & Captainnapwnli
    5. 2024now
      CTF InstructorCyberChallenge.IT @ UNINA

    Education

    1. 2025now
      Industrial PhD, Information Technology & Electrical EngineeringUniversity of Naples Federico II
    2. 2023–25
      MSc Computer Engineering, Cybersecurity110/110 cum laude, special commendationClusit Thesis Award 2025 · 3rd nationally, and remarks from Italian Intelligence for its national-security relevance
    3. 2020–23
      BSc Computer Engineering110/110 cum laude · thesis on vulnerabilities in AI code generators

    Programs & recognition

    1. GDG on Campus LeadGoogle Developer Groups · UNINA
      2025
    2. MemberCisco DTLab & Maticmind
      2024
    3. Cybersecurity ScholarshipCisco Networking Academy
      2024
    4. Apple Foundation ProgramApple Developer Academy · UNINA
      2024
    FIG. 05Based in Naples · working with CYBER RANGES (Stafford, VA) · formerly Alias Robotics (Vitoria-Gasteiz)
    Cybersecurity AIAgentic Red TeamingAdversary Emulation Blue Team OpsDFIRCTFsCyber RangesOT Security
    06

    Contact

    Let's talk, research, collaborations, CTFs.