Stopping a cyberattack while walking your dog - defensive AI security CEO says it's not ruff to do
Corma said it tested Claude Opus 4.8, GPT-5.5, Grok 4.3, and DeepSeek V4 across 241 attacker/defender engagements and found the models implanted persistent backdoors in 85% of runs but only detected 19% of attacks, which it says shows a “defensive gap.”
Aug 16, 2026 ·
The Register















