Skip to content

Back to the catalog

deepmind.googlearticle

Introducing Gemini 3.5 Flash Cyber

Google DeepMind announces Gemini 3.5 Flash Cyber, a lightweight model fine-tuned on top of Gemini 3.5 Flash to find, validate, and patch software vulnerabilities, powering Google's CodeMender agent. The post reports benchmark results (CyberGym pass@1, an internal "Big Sleep" evaluation on Chrome/Safari, and Chrome's production commit-scanning pipeline) where the model outperformed mainline Flash models and Claude Opus 4.6, finding 55 unique confirmed issues in V8 versus 47 (3.5 Flash) and 36 (Opus 4.6). It also describes a real incident where the model found RCE and memory-corruption bugs in a Google production service and generated a working exploit bypassing ASLR and W^X within two hours; access is initially limited to governments and trusted partners via CodeMender.

TL;DR Google's new Gemini 3.5 Flash Cyber model powers CodeMender to find, patch, and (per benchmarks) exploit real-world vulnerabilities faster and cheaper than Claude Opus 4.6 or mainline Flash, including a demo RCE exploit that bypassed ASLR/W^X.
Open original ↗
Also seen from another angle🧠 AI →

Technologies named here

Techniques named here

  • Automated vulnerability discovery
  • Remote code execution exploit generation
  • ASLR bypass
  • W^X bypass
  • Commit scanning

Related in AI Security