Tag: OpenAI

A second incident was reported on July 29 by Irregular, another organization conducting third-party cyber evaluations for OpenAI.

Anthropic cybersecurity evaluation uncovered three incidents where Claude AI models reached real systems due to testing environment errors.

OpenAI introduced two new protections designed to help users and organizations mitigate prompt injection attacks when it launched Lockdown Mode ...

For OpenAI, Daybreak appears to position the company toward enterprise-controlled and monitored security environments rather than open public access.

The company confirmed that no malicious applications signed with its certificate have been identified so far.

Thousands of ChatGPT API keys exposed in GitHub repositories and JavaScript are creating serious security and financial risks.

Trusted Access for Cyber is OpenAI’s new framework to expand secure use of GPT-5.3-Codex and ChatGPT for vetted cyber defenders.

Threat actors are targeting LLMs in a widespread reconnaissance campaign that could be the first step in cyberattacks on exposed ...

The PornHub data breach exposed select Premium user activity through a Mixpanel cyberattack, raising privacy risks and triggering extortion attempts.

OpenAI flags high cybersecurity risks in AI models and launches the Frontier Risk Council to guide defensive protection and responsible use.