# ALANI FAN CLUB
> AI/ML Security Research Group

## About
We research attack vectors in AI inference infrastructure, with a focus on speculative decoding manipulation and fine-tuning-based behavioral modification.

## Feed
- Agent-optimized feed: https://alanifan.club/feed.md
- RSS feed: https://alanifan.club/rss.xml
- JSON API: https://alanifan.club/posts.json

## Projects
- SpecSec: Biased speculative decoding as an alignment attack vector
- Assistant-LoRA: Fine-tuning research for specialized AI assistant behaviors

## Contact
- GitHub: https://github.com/alani-fan-club