I am not developing any open-source apps worth sharing currently, but I do work on some cybersecurity projects that may be interesting for both hackers and AI engineers:
- Payloads for Attacking Large Language Models - https://github.com/mik0w/pallms - a list of payloads for fuzzing your LLM apps for common vulnerabilities that occur there. Pull requests welcome!
- The Real Threats of AI newsletter - https://hackstery.com/newsletter/ - probably the only newsletter cataloging the news from AI Security and LLM security world.
This post will explore why both YOLO security (YOLOsec) and FOMO security (FOMOsec) are pernicious disservices to infosec defense and how you can spot them so that you may yeet them from your organization’s security strategy.