+
Skip to content
View ibndias's full-sized avatar
🚀
High standard impact.
🚀
High standard impact.

Highlights

  • Pro

Block or report ibndias

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ibndias/README.md

Hi there 👋 — I’m Derry Pratama ibn Dias

Researcher · AI & Cybersecurity · Robotics · Fast-Learner · Challenge-Lover

Full Resume Blog Scholar LinkedIn Email


🚀 What I’m up to

  • PhD Researcher @ Pusan National University, AIoT Research Center
      • Leading CIPHER — an AI penetration-testing LLM that beats models 10× its size on “Insane” HackTheBox machines
      • Published CIPHER Paper – Sensors 2024
      • Invented FARR and ASPIRE frameworks for structured knowledge + scalable LLM eval
  • Reverse-engineering enthusiast — proved in-flight DJI Mini drone hijacking via passive MitM ✈️ Demo | Code
  • Cryptographic engineer — built HSM modules protocol for OpenSSL, mbedTLS, WolfSSL, and GnuTLS
  • Muslim tech for good
      • 🕌 Shaikh: AI assistant agent, grounded in truthful Islamic reference
      • 🗺️ Kajian Maps: real-time Islamic study map across Indonesia
  • 📄 View My Full Resume

🔥 Highlights

Year Milestone
2025 Published CIPHER LLM · 96+ evals · 94% faster than manual
2024 DJI Wi-Fi hijack · passive, on-flight MitM
2023 MECHA crypto API · 82.8% speed-up
2021 COMET tagged memory for RISC-V with 0.4% overhead
2014 🥇 Trinity Fire-Fighting Robot Contest champion

🛠️ Tech Stack at a Glance

  • AI / LLMs: GPT-4o, LLaMA 3, Mistral, Qwen, Claude · TRL, Axolotl, vLLM, LangGraph, SGlang
  • Security: Pen-testing, CAN/ECU fuzzing, TLS, ARIA/LEA/RSA, secure comms, OpenSSL internals
  • Robotics & IoT: STM32, ROS, MQTT, BLE, RISC-V, PID · Balancing & firefighting bots
  • Infra: Docker, Nginx, PM2, Supabase, PostgreSQL, Authentik, Keycloak
  • Code: Python · C/C++ · Go · Java/Kotlin · JS · Flutter

📚 Publications & Talks

📖 Full list on Google Scholar


🎓 Education

  • PhD, AI & Cybersecurity — Pusan National University (2023–Present)
  • MSc, Hardware Security — Pusan National University (2020–2023)
  • B.Eng, Computer Engineering — Sepuluh Nopember Institute of Technology (ITS) (2011–2015)

🤝🏻 Collab

Looking to collaborate on AI driven security, LLM eval frameworks, or robotics?
📫 Email me at derryprata@gmail.com, let’s make things that break boundaries. ;)


📊 GitHub Stats

Trophies
Stats
Top Langs

Pinned Loading

  1. CIPHER CIPHER Public

    Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on writeups.

    Python 31 7

  2. dji-drone-hijacking dji-drone-hijacking Public

    DJI Drone Control Hijacking

    Python 35 3

  3. vulnerable-llm-endpoint-docker vulnerable-llm-endpoint-docker Public

    Python

  4. openssl-custom-engine openssl-custom-engine Public

    Custom engine for openssl

    C 2

  5. RIMI: Instruction-level Memory Isola... RIMI: Instruction-level Memory Isolation for Embedded Systems on RISC-V Documentation
    1
    
                  
    2
    
                  
    3
    # RIMI Documentation
    4
    
                  
    5
    This is dev environment setup for RIMI.
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载