German
link to LinkedIn profile link to Youtube channel link to uTest profile (login required)
photo

Martin Fürholz

Principal Security Architect & AI Red-Teaming Lead

Rostock, Germany

High-Performance Security Leadership & Agentic AI Development

The Technical Backbone of Modern Security Testing.
As the exclusive Technical Lead for the Applause Security Practice, I act as an Active Principal: I don't just architect frameworks; I lead from the front with elite manual exploitation skills. Pioneer in the development of custom Agentic AI security tools that revolutionize testing efficiency. The definitive authority on high-risk scopes: Network Infrastructure, IoT, DRM, and AI Red-Teaming.

Current Impact & Role:

Exclusive Security Test Team Lead (Applause/uTest):
Acting as the singular technical safety net. I personally handle the deepest technical dives that others cannot solve. Recent benchmark: Identified 28 critical vulnerabilities in a single US Banking Subnet (Dec 2025).

Developer of Agentic AI Systems:
Building autonomous, bespoke AI agents (C#/Python) to automate complex reconnaissance and exploitation tasks beyond human speed.

Core Competencies & Innovation:

Deep-Dive Infrastructure & Network Pentesting: Mastery of manual enumeration (Nmap/Wireshark), protocol analysis, and exploitation of complex network environments without relying solely on automated scanners.

AI Red-Teaming & Jailbreaking: Defining the playbook for testing LLM safety and robustness since day one.

Full-Spectrum Coverage: From low-level IoT Hardware & DRM reversing to high-level Web & Mobile App security.

Language: Native German, Fluent English, Conversational French (B1).

ABOUT ME

Personal Details

NAME:

Martin Fürholz

Residence:

Rostock, Germany (since 2012)

Born:

July 18, 1980 in Vienna, Austria

Occupation:

Principal Security Architect, Test Team Lead,
Professional Trainer & Subject Matter Expert

Driver's License:

European Type B (own vehicle available)

Professional Competencies

Elite Security Leadership: Exclusive Test Team Lead for the uTest Security Practice since 2018.

Proven Track Record: Over 1500 verified vulnerabilities reported; architect of full-scale API & Security Testing curricula for uTest Academy.

Advanced Penetration Testing: Expert mastery of Network/Infrastructure Testing, Web/Mobile/IoT Security, and AI Red-Teaming (LLM Jailbreaking & Robustness).

Development & Scripting: Deep proficiency in C#, C++, Java, Python, and Wolfram Language for custom tool development.

Technical Foundation: ECDL Advanced Expert (since 2007) – Certified mastery of Office productivity suites, Databases, and Presentation tools.

Interests and Hobbies

Sport:

Wakeboarding (Competitive level), Trail Running, Skiing/Snowboarding

Music & Arts:

Multi-instrumentalist (Piano, Drums, Bass, Synth) & Producer. Collaborations with international artists (e.g., London Community Gospel Choir). Early education in Photography (Graphische Vienna).

Broadcasting & Media:

Owner of a professional in-house production studio (set up late 2025) featuring 4K camera gear, teleprompter, studio lighting, and sound isolation. Currently producing high-fidelity content for upcoming channels on Security and Digital Business.

Science:

Astronomy (Observatory access via iTelescope.net), Drone Photography, and Philosophy.

Short Biography

Martin Fürholz is a Principal Security Architect and the exclusive Test Team Lead for the uTest Security Practice. Since 2018, he has served as the technical backbone for global testing operations, ensuring delivery quality across high-risk scopes including AI Red-Teaming, IoT ecosystems, and critical infrastructure. Beyond his leadership role, Martin is a hands-on expert with over 1500 reported vulnerabilities and a deep background in software development (C#/C++/Python) dating back to 2000.

He combines this technical depth with strong pedagogical skills, having authored comprehensive training courses for the uTest Academy and served as a professional lecturer for IT Security. Martin grounds his cutting-edge security work in solid administrative proficiency (ECDL Advanced Expert since 2007) and diverse creative talents as a musician and photographer. He is currently pursuing a Bachelor’s degree in Digital Business to further bridge the gap between technical execution and strategic management.

Continuing Education

B.A. Digital Business (English)
IU International University of Applied Sciences (since August 2024)

Offensive Security Certification (OSWE/WEB-200)
Preparation ongoing, exam scheduled for Fall 2026

NOTABLE ACCOMPLISHMENTS & PROJECTS

from

2023

TO

Present

(3 Years)

Agentic AI Development

GoingLLM: The Autonomous Intelligence Backbone

Visionary Timing: I architected and deployed GoingLLM in early 2023. Recognizing the limitations of static models early on, I built the solution the market was missing: an autonomous agent capable of intelligent, live reconnaissance.

The USP Today – Dark Web & Deep Research: While basic web search is now a commodity, GoingLLM remains my proprietary advantage for deep-dive intelligence. It is engineered for autonomous Dark Web research and complex data correlation.

Enterprise Impact: GoingLLM currently serves as the engine for high-stakes security engagements. Case in point: I utilize this tool to deliver critical, real-time intelligence on piracy and DRM circumvention trends for the C-Level security division of a global Top-5 Film Studio. It allows me to answer questions that commercial AI tools simply refuse to touch.

Today, GoingLLM acts as the "neural backbone" for my entire suite of custom agentic testing tools, continuously updated to leverage GPT-5, various Search APIs, and advanced crawling logic.

Visit Project Website: goingllm.com

GoingLLM Architecture

from

2018

TO

Present

(8 Years)

Strategic Leadership

Building the Future: AI Red-Teaming & Global Security Operations

Architect of the AI Red-Teaming Practice (since 2024): When the industry shifted towards Generative AI, I independently designed and built the entire Red-Teaming framework at Applause from the ground up.
I owned the full lifecycle: Creating Cycle Overviews, managing tester budgets, and developing the foundational Test Cases for safety and jailbreaking. I personally executed the initial engagements, handled the triage, and defined the reporting standards for multimodal models (Text, Audio, Image). What began as a one-man initiative is now the standard operating procedure.

Exclusive Team Lead (The Technical Anchor): As the Test Team Lead for the Security Practice since 2018, I serve as the operational and technical anchor. I don't just manage tickets; I guarantee the integrity of the testing process. I act as the escalation point for the most complex technical challenges—from IoT hardware attacks to intricate DRM bypasses.

Scaling Excellence: I have transformed the team's capabilities by providing repeated, high-level training (up to 6-hour workshops) and creating the official security curriculum for the uTest Academy. My leadership ensures that despite high fluctuation in the gig-economy, our delivery quality remains at an elite level.

from

2025

TO

Present

(1 Year)

Advanced AI Research

IMMER: Organic Neural Architecture & Agentic Engineering

The Project (Stable Research Artifact v3.8): I am currently finalizing "IMMER" (Intelligent Multi-scale Memory via Emergent Resonance), an experimental architecture designed to solve the static nature of LLMs. Unlike simple RAG, IMMER implements Test-Time Neurogenesis and Metabolic Aging. The neural net physically grows and crystallizes knowledge during interaction, preventing catastrophic forgetting.

The Innovation – Efficient Plasticity: While inspired by Google's "Titans", I architected IMMER to run on consumer hardware (e.g., RTX 4080). Instead of modifying heavy attention heads, my system feeds dynamic memory states via "Soft Tokens" into a frozen core (Qwen). The result: A system that becomes smarter than its core within single-digit turns.
(Paper and proprietary release scheduled for late 2026)

The Engine – Agentic Training (MAKER): To train this organic system reliably, I leverage the MAKER framework. It solves the hallucination problem by process: breaking jobs into micro-tasks, implementing multi-agent voting, and enforcing strict JSON schema validation. If an output is flawed, it is automatically rejected and re-rolled. This ensures near-zero error rates even with smaller models.

from

2016

TO

Present

(10 Years)

Education & Execution

Mastery Through Teaching: Professional Training & Technical Excellence

Professional Lecturer (Alfatraining GmbH, 2021-2022): True mastery is proven when you can teach it. I served as the official ISTQB Trainer for Alfatraining, conducting full-time, 4-week intensive courses for IT managers, police officers, and admins.
I taught the full spectrum: From ISTQB CTFL Software Testing basics to advanced CompTIA Pentest+ certification preparation. My curriculum covered deep-dive technical subjects including Nmap scanning strategies, HTTP protocol analysis, and web application attacks.

Pentesting Excellence: This educational background is grounded in active field experience. My track record includes securing internal banking infrastructures, reversing IoT protocols, and finding critical logic flaws in DRM systems. I don't just run tools; I understand the underlying mechanics well enough to explain them to a novice—or exploit them against a hardened target.

from

2010

TO

Present

(16 Years)

Community Impact

Open Source & Community Leadership

Guest Mentor at University of Rostock (2021-2024): Invited by the Rostocker Hackspace, I have regularly conducted voluntary workshops during the "Fachschaftswoche" for computer science students. Topics ranged from practical IT security to ethical hacking, bridging the gap between academic theory and industry reality.

Open Source Legacy: My commitment to the community spans over a decade.
Security Tools: Active contributor to projects like MobSF and Security Stack Exchange.
Developer Roots: Created widely-used Firefox add-ons for image collecting and contributed code to Second Life Viewers (incl. JIRA bug moderation) from 2010–2015.

Whether mentoring students or submitting pull requests, my goal remains the same: sharing knowledge to build a more secure and open digital ecosystem.