Cybersecurity
Doppel’s AI defense system stops attacks before they...
Doppel uses GPT-5 and reinforcement fine-tuning to stop deepfake and imperson...
Disrupting malicious uses of AI: October 2025
Discover how OpenAI is detecting and disrupting malicious uses of AI in our O...
Combating online child sexual exploitation & abuse
Discover how OpenAI combats online child sexual exploitation and abuse with s...
OpenAI and Anthropic share findings from a joint saf...
OpenAI and Anthropic share findings from a first-of-its-kind joint safety eva...
Estimating worst case frontier risks of open weight ...
In this paper, we study the worst-case frontier risks of releasing gpt-oss. W...
Understanding Prompt Injection Vulnerabilities in AI...
Prompt injection represents a critical vulnerability in machine learning syst...
Introducing Advanced Account Security
Introducing Advanced Account Security: phishing-resistant login, stronger rec...
Cybersecurity in the Intelligence Age
OpenAI outlines a five-part action plan for strengthening cybersecurity in th...
Our response to the Axios developer tool compromise
OpenAI responds to the Axios supply chain attack by rotating macOS code signi...
Designing AI agents to resist prompt injection
How ChatGPT defends against prompt injection and social engineering by constr...
Disrupting malicious uses of AI | February 2026
Our latest threat report examines how malicious actors combine AI models with...
Introducing Trusted Access for Cyber
OpenAI introduces Trusted Access for Cyber, a trust-based framework that expa...
Our response to the TanStack npm supply chain attack
OpenAI details its response to the TanStack “Mini Shai-Hulud” supply chain at...
Accelerating the cyber defense ecosystem that protec...
Leading security firms and enterprises join OpenAI’s Trusted Access for Cyber...
Keeping your data safe when an AI agent clicks a link
Learn how OpenAI protects user data when AI agents open links, preventing URL...
Trusted access for the next era of cyber defense
OpenAI expands its Trusted Access for Cyber program, introducing GPT-5.4-Cybe...
