Jonathan Evertz
Doctoral Researcher at CISPA Helmholtz Center for Information Security
North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolJonathan Evertz is a doctoral researcher at CISPA Helmholtz Center with eight years of experience at the intersection of machine learning, software engineering, and security. His work focuses on the security and privacy of modern ML systems, especially adversarial machine learning and vulnerabilities in large language models. He has driven hands-on research from hardware reversing of deep-learning FPGA cores to building open-source tooling for robotics and low-power embedded inference. International experience includes an exchange stint at the University of Tsukuba where he organized a multi-university workshop, reflecting both technical depth and community-building. Known for "riding down the gradients" and deliberately breaking systems to learn their failure modes, he brings a pragmatic, attack-first mindset to building more robust ML systems.
8 years of coding experience
5 years of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Ruhr University Bochum
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (40)
prompt-injection9
adversarial-learning9
security8
toolbox7
pytorch7
boolean7
graph7
benchmarking7
machine-learning7
robustness7
prompt-engineering7
adversarial-machine-learning7
deep-learning7
graph-convolutional-networks7
interaction7
Programming languages (2)
Github contributions (5)
LostOxygen/llm-confidentiality
Jul 2023 - Mar 2025
Whispers in the Machine: Confidentiality in LLM-integrated Systems
Contributions:1 PR, 586 pushes, 1 comment in 1 year 8 months
chatgptconfidentialitydeep-learningframeworkgpt
LostOxygen/ReMu-Agent-Env
Mar 2022 - Jul 2022
Developing an Environment for Neural Network based Reinforcement Multi-Agent Interaction
Contributions:6 reviews, 189 commits, 28 PRs in 3 months
interactionpythondevelopingagentdeep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.