Checked fact 157415 Oct 2026Safety and security

Google DeepMind says Gemini 4 Argon leads on Gray Swan's Indirect Prompt Injection benchmark, cutting attack success across 15 adaptive attempts to 0.7%.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Argon leads in prompt injection robustness on Gray Swan's Indirect Prompt Injection (IPI) benchmark, cutting attack success across 15 adaptive attempts to 0.7%.

What the source said when we opened it, on 15 Oct 2026.

The source

Developing Gemini 4 Argon responsibly and safely
Google DeepMind · 2026-10-13

Open the source archived copy

Checked

Checked by the notis newsroom on 15 Oct 2026, against the source above.

The number in it

0.7% · gemini-4-argon, benchmark score (Gray Swan Indirect Prompt Injection, attack success across 15 adaptive attempts (lower is better))

In the story

Google DeepMind puts next-generation safeguards around Gemini 4 Argon 15 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Google DeepMind says Gemini 4 Argon leads on Gray Swan's Indirect Prompt Injection benchmark, cutting attack success across 15 adaptive attempts to 0.7%.” ai notis, checked 15 Oct 2026. Source: Developing Gemini 4 Argon responsibly and safely (Google DeepMind). https://ainotis.com/c/1574

As a reference (APA style)

ai notis. (2026, October 15). Google DeepMind says Gemini 4 Argon leads on Gray Swan's Indirect Prompt Injection benchmark, cutting attack success across 15 adaptive attempts to 0.7% [Checked claim 1574]. ai notis. https://ainotis.com/c/1574

Anyone may quote this address. It does not change; if we correct the story, this page says so.