Dr. Erwin Quiring // whoami

Dr. Erwin Quiring

Senior Consultant & AI Research Scientist · _fbeta

I help organizations build AI systems that actually hold up: reliable, efficient, and secure by design.

View publications
profile.py
class ErwinQuiring:
role = "AI Research Scientist"
focus = ["reliability", "efficiency", "security"]
​
def mission(self):
return "AI that does what it should."
// about

Focus areas

I'm a senior consultant and AI research scientist focused on training, securing, and deploying AI systems that hold up in the real world. I previously held postdoctoral positions at Ruhr University Bochum and ICSI, an affiliated institute of the University of California (UC Berkeley), and earned my PhD from TU Braunschweig in trustworthy AI and machine learning security.

My work spans training and fine-tuning ML models and LLMs, defending against adversarial threats and deepfakes, building agentic AI pipelines, and guiding organizations from use-case discovery to production deployment — bridging rigorous research with real-world impact.

AI Training

Training and fine-tuning ML models and LLMs — carefully avoiding the subtle pitfalls that quietly undermine AI reliability — and creating plausible synthetic data.

AI Security & Trust

Hardening AI against manipulation and adversarial threats — from poisoning to evasion and prompt injection — plus detecting deepfakes & AI-generated content, and considering AI regulation.

Agentic AI

Designing and deploying AI agent pipelines — and using AI agents to accelerate software development.

AI Deployment & Enablement

Guiding organizations in applying AI — from use-case identification to deployment, including enablement workshops and AI operating models.

// education

Education

  • PhD, Computer Science (with distinction)
    TU Braunschweig · Trustworthy AI & machine learning security
  • MSc, Computer Science (with distinction)
    Universität Münster
  • BSc, Information Systems (best graduate)
    Universität Münster
// skills

Skill overview

AI Agents

LangGraph / LangChain • Codex • Claude Code • n8n

AI-related Regulation

AI Act • CRA

Databases

SQL Database • NoSQL Database • Vector Databases

Data and Process Modeling

BPMN • EPK • UML

AI

AI Frameworks & Ecosystems

PyTorch • TensorFlow • Transformers • HuggingFace • Unsloth

Classical ML & Data Science

scikit-learn • XGBoost • Pandas • NumPy • SciPy • Gensim

Programming & Systems

Python • R • C • C++ • SQL • Java • Bash • Unix • Git / GitHub • Container & Virtualization

AI Infrastructure

Azure

// publications

Recent publications

View all publications →

ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering

Denis Lukovnikov, Andreas Müller, Erwin Quiring, Asja Fischer
2026 Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Link

Chasing Shadows: Pitfalls in LLM Security Research

Jonathan Evertz, Niklas Risse, Nicolai Neuer, Andreas Müller, Philipp Normann, Gaetano Sapia, Srishti Gupta, David Pape, Soumya Shaw, Devansh Srivastav, Christian Wressnegger, Erwin Quiring, Thorsten Eisenhofer, Daniel Arp, Lea Schönherr
2026 Network and Distributed System Security Symposium (NDSS)
Link

Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models

Jonas Thietke, Andreas Müller, Denis Lukovnikov, Asja Fischer, Erwin Quiring
2025 ICLR Workshop on GenAI Watermarking (WMARK)
Link

Intriguing Properties of Adversarial ML Attacks in the Problem Space [Extended Version]

Jacopo Cortellazzi, Erwin Quiring, Daniel Arp, Feargus Pendlebury, Fabio Pierazzi, Lorenzo Cavallaro
2025 ACM Transactions on Privacy and Security
DOI

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

Andreas Müller, Denis Lukovnikov, Jonas Thietke, Asja Fischer, Erwin Quiring
2025 Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Link
// honors

Selected honors, scholarships & awards

  • Oral Session, CVPR — "Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models" 2025
  • Best Paper Award at IEEE Deep Learning Security and Privacy Workshop (DLSP) 2024
  • Dissertation Award, AI Talent of Lower Saxony, Germany 2022
  • Distinguished Paper Award at USENIX Security Symposium 2022
  • Winner of the defender challenge at the Machine Learning Security Evasion Competition by Microsoft 2020
  • Best Student Paper Award at IEEE International Workshop on Information Forensics and Security (WIFS) 2015
  • Scholarship by German Academic Exchange Service (DAAD) 2015
  • Deutschlandstipendium (Scholarship), sponsored by BASF SE 2013–2015
  • Winner of Special Award of Münster's Society for Applied Informatics for the best empirical thesis 2013
  • Winner of Hays-AlumniUM-Bachelor-Award as the best BSc. student in graduating class 2013
// activities

Academic activities

  • Program Committee Member — leading security & ML venues (2019 – 2025)
  • Journal reviewer for IEEE and ACM security & ML journals
  • Sub-reviewer for USENIX Security, IEEE S&P, ACM CCS, and NDSS