Research & news
Dream researchers push technology to its furthest edge, building and testing breakthrough capabilities, from artificial intelligence and advanced threat hunting to malware reverse engineering, and vulnerability research in existing and emerging attack surfaces.
Operating at the frontier of cyber and artificial intelligence research, we turn bold ideas into working innovation that strengthens how nations anticipate, understand, and neutralize the most complex threats.
Arad Inbar, a security researcher from our research group at DREAM, recently presented at Black Hat Singapore. The talk focused on using protocol specifications, specifically RFCs, as a primary surface for vulnerability discovery.
One of the most powerful ways to understand what a security patch actually fixes is to reverse engineer the binaries before and after the update. Vendors rarely disclose full vulnerability details immediately, but the code always tells the truth. By performing a binary diff, researchers can quickly identify which parts of the code changed and infer the class of vulnerabilities that the patch mitigates.
We built an AI agent for security teams. It analyzes configs, hunts for vulnerabilities, investigates threats. Here’s what we underestimated: security people are paid to be paranoid. They don’t trust systems they can’t audit.And honestly? They shouldn’t.So we built an explainability layer. Not just “here’s what we found” but “here’s why we think that, and here’s how you can check.”Here’s what worked, what didn’t, and what surprised us.
A bug rooted in Telnet's early-1990s LINEMODE logic survived into modern GNU Inetutils telnetd, leaving a pre-auth memory corruption path reachable before /bin/login, before passwords, and before PAM.
A vulnerability scanner trusted to protect a CI pipeline was the entry point. An AI proxy handling your LLM API keys was the target. The credentials stolen from the first were used to compromise the second - and the cascade didn't stop there.