{"author_url":"https://blog.hatena.ne.jp/fltech-user/","type":"rich","title":"Is GPT-5 Easier to Jailbreak \u2014 or Are We Assessing It Wrong? A Comprehensive Assessment of GPT-5 Security Risks Using Fujitsu\u2019s LLM Vulnerability Scanner","description":"Hello, we are Omer and Roman from the Generative AI Trust Research team at Fujitsu\u2019s Data & Security Research Laboratory. We\u2019re excited to share our latest work: the first comprehensive security evaluation of GPT-5, conducted using our Fujitsu's LLM Vulnerability Scanner. This report dives deep into\u2026","version":"1.0","url":"https://blog-en.fltech.dev/entry/2025/08/22/gpt-5-sec","height":"190","provider_name":"Hatena Blog","width":"100%","blog_title":"fltech - Technology Blog of Fujitsu Research","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fblog-en.fltech.dev%2Fentry%2F2025%2F08%2F22%2Fgpt-5-sec\" title=\"Is GPT-5 Easier to Jailbreak \u2014 or Are We Assessing It Wrong? A Comprehensive Assessment of GPT-5 Security Risks Using Fujitsu\u2019s LLM Vulnerability Scanner - fltech - Technology Blog of Fujitsu Research\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","published":"2025-08-25 08:43:12","categories":["Security","AI"],"provider_url":"https://hatena.blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/f/fltech-user/20250820/20250820112933.png","blog_url":"https://blog-en.fltech.dev/","author_name":"fltech-user"}