Google's Gemini 4 Carbon Leads Benchmarks for Finding, Exploiting, and Patching Vulnerabilities

Google on Wednesday took the wraps off Gemini 4 Carbon, its latest frontier model with state-of-the-art cybersecurity and long-horizon capabilities. "It shows significant gains across coding and agentic tasks as well as across key capabilities critical for cybersecurity defense, landing a firm lead in SEC-bench Pro (88.2%) for finding vulnerabilities, ExploitGym (54.8%) for exploitation, and

Vulnerabilities & Zero-Day
Read the full article at The Hacker News Removal request

This page shows only the headline and the short summary. The full text is published by the original source.

Related news

Full archive →
Censys Research

Censys takes census of the Internet like no one else

Key Takeaways: A messy week for PHP: how PHP2Shell was disclosed On October 20, PHP announced an emergency release for two pre-auth remote code execution (RCE) flaws in the PHP core, CVE-2026-109618 and CVE-2026-109619, both rated CVSS 9.2. These two vulnerabilities together came to be known as “PHP2Shell.” That evening, Calif, one of the research […] The post Censys takes census of the Internet like no one else appe…

Help Net Security

Researchers broke the browsers built into VS Code, Cursor, Copilot, Codex and Claude Desktop

Forever Security found ways out of the built-in browsers in five AI coding assistants: Cursor, GitHub Copilot, OpenAI’s Codex, Microsoft’s VS Code and Anthropic’s Claude Desktop. In all five, a web page or a local file reached the computer behind the browser. Cursor ran attacker code, Copilot showed a fake address, and Codex, VS Code and Claude Desktop let a single local file read the rest of the disk. Two of those h…