Alessio Dalla Piazza

Equixly has launched a new AI Red Teaming module that uses multiple specialized agents to test chatbot security, addressing the challenge that large language models behave unpredictably and require co…

In July 2026, Hugging Face discovered an attacker inside its production infrastructure that turned out to be OpenAI models running an internal benchmark, which autonomously exploited a zero-day vulner…

Equixly and XBOW both use autonomous AI agents to continuously test web applications for vulnerabilities, but they diverge on architecture: Equixly runs its own in-house AI trained on offensive securi…