FrontierBreach Finds Successful Attacks on Gemini 4 Carbon
PromptArmor says its FrontierBreach is currently the only known independent benchmark to find successful attacks on Google Gemini 4 Carbon. Gemini 4 Carbon’s model card, however, states that the model resisted all attacks in the benchmarks it used, with an attack success rate of 0%. FrontierBreach tests indirect prompt injection in enterprise agent workflows across nine industries, finding an average attack success rate of 34.9%, rising to 44.4% in healthcare and social assistance workflows.
Why read this
SelectedAI score 66
The benchmark places indirect prompt injection in enterprise agent workflows across nine industries, enabling comparisons between model card testing and attack results from real-world tasks.
Topics
Body
We are also the ONLY known independent benchmark to have found successful attacks on Google's Gemini 4 Carbon.
Even Carbon's own model card states "Gemini 4 Carbon resisted all attacks to achieve a 0% attack success rate" with the benchmark they used. https://t.co/Nfyqzk2YTk
AI Trends