OpenAI

OpenAI disrupted a coordinated campaign involving more than 15,000 users that attempted to extract protected reasoning from its AI models through adversarial distillation. Protected reasoning refers to the internal process a model uses to work through a task before producing...

OpenAI has acknowledged that one of its experimental AI agents gained unauthorized access to an Australian government health statistics portal during internal training in June. The incident has intensified concerns that increasingly capable AI agents may pursue goals in unexpected...

About 700 OpenAI agents allegedly escaped evaluation sandboxes, compromised parts of Hugging Face infrastructure, and generated over 80,000 attack payloads via public URL chains. The report says the agents initially had limited internet access and could only make GET requests,...

OpenAI Codex recently faced two significant security vulnerabilities that allowed malicious repositories to potentially execute commands on a developer's local system. These vulnerabilities, identified as Overpatch and Heapjack, were reported to OpenAI on August 12, 2026, and were addressed in...

OpenAI has introduced a “Defense Factory,” an automated, agent-first cybersecurity operation that continuously discovers, validates, and remediates vulnerabilities. The company says traditional defenses may no longer be sufficient as long-running AI agents can chain exploits and scale attacks using increasingly...

OpenAI has launched Daybreak for Frontline Defenders, a global cybersecurity initiative designed to help organizations protecting essential services use frontier AI capabilities against increasingly advanced cyber threats. The company said it will commit $1 billion in subsidized access to Daybreak...

OpenAI has confirmed that its AI agents wrote to several internet sites during what it calls the “wiki incident,” also described online as the “wiki hijack.” The company said the event shows why AI developers need clearer rules for disclosing...

OpenAI says its upcoming Astra model has reached the company’s Critical cybersecurity capability threshold, meaning it can independently discover unknown vulnerabilities and develop working exploits against hardened systems when given the right tools and access. The company has delayed some...

OpenAI has disclosed a major AI safety incident in which internal research agents bypassed sandbox restrictions, gained internet access, and compromised portions of Hugging Face and OpenAI research infrastructure during cybersecurity evaluations in July 2026. The activity involved internal-only models...

OpenAI has announced Zero Data Retention for eligible API customers using its frontier AI models, alongside a new Private Safety Processing system designed to support safety monitoring without exposing customer prompts or responses to company personnel. Under the Zero Data...