Blog

Explore ChatGPT pentesting limits: blind spots, false positives, compliance risks, and how to validate findings safely.

AI red teaming helps defense teams test models, expose attack paths, and harden systems faster with measurable risk reduction, now.

A new feature in the Novee platform that autonomously tests AI-enabled systems the way real attackers do, and discovers vulnerabilities before they’re exploited.

How we turned hundreds of broken open-source apps into deterministic training environments

Claude Code Security represents a tremendous move forward for AI code scanning, but finding vulnerabilities in static codebases – even at machine-speed – is not how real attackers operate.

Our researchers found 3 critical vulnerabilities in PDF ecosystems. Then we let our trained AI loose, and found 13 more.

Inside Novee’s approach to scaling zero-day discovery by compounding exploit reasoning across modern PDF platforms.

In live-browser exploit benchmarks, Novee’s 4B-parameter model achieved up to 90% accuracy, outperforming Claude 4 Sonnet and other frontier LLMs by over ~55%.

Modern web apps layer defenses so thick that XSS should be impossible. Attackers still find ways through. We wondered: could we teach AI to probe, adapt, and reason its way…