Hacktron AI Lab
What happens when an LLM is given the same resources and tools as a human security researcher?
This question guides everything we do.
Key Research Areas
AI Security Agents
Developing and assessing LLM agents capabilities in finding vulnerabilities.
Benchmarking Frameworks
Creating standardized benchmarks to test and evaluate AI security capabilities across various scenarios.
LLM-Assisted Tools
Building tools that enhance the capabilities of human security researchers through AI assistance.