▲ 3 ▼ OpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker” (techcrunch.com) submitted 11 months ago by Mazdak@lemmy.org to c/technology@lemmy.org comment fedilink hide all child comments
▲ 17 ▼ OpenAI says AI browsers may always be vulnerable to prompt injection attacks (techcrunch.com) submitted 11 months ago by yoasif@fedia.io to c/firefox@fedia.io 1 comment fedilink hide all child comments 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."