OpenAI Blog

OpenAI and Hugging Face address security incident during model evaluation

OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.

A thousand fewer paths to root

OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.

OpenAI o1 system card

This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.

Fighting the New York Times' invasion of user privacy

OpenAI is fighting the New York Times’ demand for 20 million private ChatGPT conversations and accelerating new security and privacy protections to protect your data.

The Hugging Face incident and the road ahead

OpenAI shares findings from the Hugging Face security incident and the steps we’re taking to strengthen AI model security, monitoring, and alignment.

OpenAI Adopts Google's SynthID Watermark for AI Images with Verification Tool

OpenAI advances AI content provenance with Content Credentials, SynthID, and a verification tool to help people identify and trust AI-generated media.

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them…

OpenAI Privacy Filter

OpenAI Privacy Filter is an open-weight model for detecting and redacting personally identifiable information (PII) in text with state-of-the-art accuracy

How we’re responding to The NYT’s data demands in order to protect user privacy

OpenAI is fighting a court order at the demands of The New York Times and plaintiffs, which involves retention of consumer ChatGPT and API user data indefinitely. Learn how we’re working to uphold user privacy, address legal requirements, and stay true to our data protection commitments.

Patch the Planet: global response coordination as agents uncover vulnerabilities

Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities across open source.

OpenAI DayBreak – GPT-5.5-Cyber

OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.

Concrete AI Safety Problems

We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as intended.

Responding to the next frontier of critical cyber capabilities

OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.

Path to Astra: critical capabilities and frontier safeguards

Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.

Pacing model development in an era of cyber-critical capabilities

OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.

GPT‑5.5 Bio Bug Bounty

Details about the OpenAI Bio Bounty program

Securing our frontier model training environment

OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.

GPT 5.6 Cyber

Meet GPT-5.6-Cyber, OpenAI’s cybersecurity-specific model available through Daybreak Red for authorized vulnerability research, exploit validation, and security testing.

Disrupting malicious uses of AI by state-affiliated threat actors

Teen safety, freedom, and privacy

Explore OpenAI’s approach to balancing teen safety, freedom, and privacy in AI use.

OpenAI's response to the Axios developer tool compromise

OpenAI responds to the Axios supply chain attack by rotating macOS code signing certificates, updating apps, and confirming no user data was compromised.

Due to concerns about malicious applications, GPT2 will not be released (2019)

We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.