AI Security Research Lab
KANTILABS
AI Security Research and Offensive Security Models
Kanti Labs is an AI security research lab building open-weight models, datasets, and research for offensive web security.
What Is Kanti Labs?
Kanti Labs is an AI security research lab focused on open-weight models, datasets, and public write-ups for offensive web security.
About Kanti Labs
What Kanti Labs is, who operates it, and how the brand shows up across the web.
Read the Kanti Labs story
Kanti Labs Models
Open-weight offensive security models trained for web exploitation research and local deployment.
Explore Kanti Labs models
Research from Kanti Labs
Training notes, evaluation methodology, roadmap updates, and offensive AI security thinking.
Read Kanti Labs research
Contact Kanti Labs
Reach Kanti Labs for collaboration, sponsorship, research questions, or model discussions.
Get in touch with Kanti Labs
Kanti Labs Models
Open-weight offensive security models fine-tuned for web exploitation research, local inference, and Strix-based workflows.
kanti-xss-sft-4b
Supervised fine-tuned on curated XSS synthetic Strix traces from real vulnerabilities. Designed to be used as a Strix sub-agent.
kanti-xss-rl-4b
Reinforcement learning variant trained with reward signals from simulated XSS validation. Designed to be used as a Strix sub-agent.
Research from Kanti Labs
Public write-ups on training methodology, release reasoning, and offensive AI security experiments.
Building a Hacker
Dataset curation and standard fine-tuning details for the first iteration of the Strix XSS model series.
A Week of RL
The process of creating a reinforcement learning environment for training and evaluating models that find XSS vulnerabilities.
Research Roadmap
Where Kanti Labs has been and what the next model and research releases are aiming toward.
XSS Foundation Models
Released SFT and RL 4B-parameter models for XSS payload generation. Established training pipeline, dataset curation, and evaluation methodology.
Full Post-Training Run
Completing comprehensive post-training with expanded datasets and improved reward modeling. The next Kanti Labs model release is the near-term milestone.
Scale and Expand
Scale to larger dense and MoE architectures, then expand beyond XSS into SQLi, SSRF, and adjacent vulnerability classes.
Unified Multi-Vulnerability Model
A single model capable of reasoning about multiple vulnerability families with tighter integration into defense evaluation loops.
Contact Kanti Labs
Kanti Labs is available for research collaboration, sponsorship discussions, and conversations about offensive security models.