OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery to fix issues before tools…
Tag: Fake Chain-of-Thought
GPT-5.1: Model Vulnerable to Fake Chain-of-Thought Attacks
GPT-5.1 was found to be highly vulnerable to Fake Chain-of-Thought (CoT) attacks, with success rates above 95%, but now below 10% for…