OpenAI Says Prompt Injections a Challenge for AI Browsers, Builds an Attacker to Train ChatGPT Atlas

OpenAI says prompt injections remain a key risk for AI browsers and is using an AI attacker to train ChatGPT Atlas.

OpenAI says AI browsers may always be vulnerable to prompt injection attacks

OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an "LLM-based automated attacker." ...