Red, an internal automated red-teaming system built to find prompt injection weaknesses and make AI agents safer before ...
OpenAI says GPT-Red automates prompt injection testing and helped GPT-5.6 Sol record sixfold fewer direct injection failures ...
OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...
Context bomb cybersecurity research from Tracebit shows that a single hidden text string inside an AWS cloud decoy stopped ...
When combined with another exploit, the "PromptFiction" vulnerability, which has been fixed, could have enabled an end-to-end attack on a targeted system.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results