Product updates
Inside Cascade 2 Iguazu: how we benchmark our AI pentesting engine
How Cascade 2 Iguazu's scheduler and shared coverage map work together, how we benchmark the engine, and what two rounds of internal benchmarks reveal.
Arnaud Fanthomme
As a Research Scientist at Escape, I help build the future of Agentic Pentesting systems. My background is in the theory of Neural Networks and Reinforcement Learning, which I now apply to Cybersecurity.
Arnaud Fanthomme — Last Publications
Research
Why does the rise of Agentic AI force security teams to become research-aware?
Bruce Schneier : "security is a process, not a product". It’s not enough to audit your application once, every new feature introduces new attack surfaces that must be taken into account when evaluating the security of the application as a whole. For example, a company rolling out a new Agentic AI process without adequate guardrails might expose themselves to MCP tool poisoning, an emerging class of attacks where malicious actors leverage the trust placed in a tool metadata to steer th
