Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
GPT-Red: Unlocking Self-Improvement for Robustness
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
Automated AI Red Teaming by Mozilla
We are building for the next generation in GenAI security and beyond.
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL-E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30% fall to near zero.
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers are poorly matched to this regime in two ways: unreliable success measurement and poor exploration. First, we find that judges widely used in prior T2I red-teaming work are unreliable under vague unsafe-content targets: they either miss true violations or reward benign borderline images on hardened APIs. We therefore define strict category-specific success criteria and calibrate strong VLM judges against human labels. Second, we show that broadly used prompt-modification pipelines do not solve the exploration problem: on harder guardrail settings they remain tied to seed prompts, fail to transfer, or cannot bootstrap positive examples. We introduce RISE, which evolves reusable strategies used to generate prompts rather than rewriting them one by one. The best discovered strategies are then reused to generate attacks across new scenarios. On DALL-E 3, Nano Banana 2 (Google) and GPT-Image-2, RISE reaches up to 13% human-verified ASR; under the same calibrated evaluation, prior methods with reported ASR as high as roughly 30% fall to near zero.
GPT-Live System Card - OpenAI Deployment Safety Hub
GPT-Live-1 and GPT-Live-1 mini are a new generation of voice models designed to make conversations with AI feel more natural and intelligent.
gpt-oss:120b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
gpt-oss:20b
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
Introducing gpt-oss-safeguard
OpenAI introduces gpt-oss-safeguard—open-weight reasoning models for safety classification that let developers apply and iterate on custom policies.
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
OpenAI technical goals
OpenAI’s mission is to build safe AI, and ensure AI’s benefits are as widely and evenly distributed as possible.
Previewing GPT-5.6 Sol: a next-generation model
OpenAI previews GPT-5.6 Sol, a next-generation model with stronger capabilities in coding, science, and cybersecurity, paired with its most advanced safety stack.
GPT-6 Astra System Card - OpenAI Deployment Safety Hub
Today, we are releasing GPT-6 Astra, the most capable model we have ever broadly deployed. Astra is our first model to reach the Critical level of cybersecurity capability under our Preparedness Framework.
Microsoft’s AI Red Team Has Already Made the Case for Itself
Since 2018, a dedicated team within Microsoft has attacked machine learning systems to make them safer. But with the public release of new generative AI tools, the field is already evolving.
GPT-6 Astra System Card - OpenAI Deployment Safety Hub
Public, mostly-static site to explore OpenAI safety evaluations, system cards, and posts.