Philipp Normann
philippnormann
PhD Candidate – AI for Cybersecurity
Languages
Loading contributions...
Top Repositories
🎯 Autonomously buy Nvidia Founders Edition GPUs as soon as they become available.
🍃 A comprehensive monitoring and alerting solution for the status of your Chia farmer and harvesters.
🔆 Script for adjusting the brightness and color temperature of displays on a software level using xrandr.
🥋 Framework for continuously improving the IT-Security of your teams through gamification and self-assessment.
🐝 Zigbee security research toolkit for the RaspBee, nRF52840 and CC2531 radio modules.
⚡ A simulation of finding the shortest charging routes for electric vehicle fleets using ant colony optimization.
Repositories
19⚡ A simulation of finding the shortest charging routes for electric vehicle fleets using ant colony optimization.
Async RL Training at Scale
🍃 A comprehensive monitoring and alerting solution for the status of your Chia farmer and harvesters.
🕵️♂️ ML project to identify malicious web payloads, aimed at boosting the effectiveness of WAFs and IDSs.
🥋 Framework for continuously improving the IT-Security of your teams through gamification and self-assessment.
🐝 Zigbee security research toolkit for the RaspBee, nRF52840 and CC2531 radio modules.
verl: Volcano Engine Reinforcement Learning for LLMs
🎯 Autonomously buy Nvidia Founders Edition GPUs as soon as they become available.
👨💻 Can you tell the favorite programming language of GitHub users, only by looking at their faces?
A web browser with dynamic data-flow tracking enabled in the Javascript engine and DOM, based on Mozilla Firefox (https://github.com/mozilla-firefox/firefox). It can be used to identify insecure data flows or data privacy leaks in client-side web applications.
🔆 Script for adjusting the brightness and color temperature of displays on a software level using xrandr.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
Democratizing Reinforcement Learning for LLMs
A comprehensive local Linux Privilege-Escalation Benchmark
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
📱 Lightweight TensorBoard client for Android and iOS created using the Flutter mobile SDK.
📕 Adversarial Attacks and Defenses for Image-Based Recommendation Systems using Deep Neural Networks.
☕ Lelit Mara X Temperature and Shot Timer Display using an ODROID-GO
📥 Download entire directories from the @fh-wedel handout server.