corca-ai/awesome-llm-security
A curated collection of research papers, tools, and resources on LLM security including adversarial attacks, backdoor defenses, and platform security.
Velocity · 7d
+1.5
★ / day
Trend
→steady
star history
This repository aggregates academic papers and open-source tools related to securing large language models. It organizes content across attack categories (white-box, black-box, backdoor), defense mechanisms, fingerprinting techniques, and platform security. The list includes benchmark resources and integrates PDF summaries from a research navigation tool for efficient paper discovery.