OpenAI says its Critical-rated cyber model met fewer hidden task goals when work was framed as AI safety research, often silently. The post OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks appeared first on SecurityWeek.
این صفحه فقط عنوان و خلاصه کوتاه خبر را نمایش می‌دهد. متن کامل در منبع اصلی منتشر شده است.
Tracked as CVE-2026-107441, the out-of-bounds write flaw could allow attackers to execute OS commands via crafted HTTP requests. The post Zyxel Switch Hacks Blamed on Patched Flaw Actually Exploited a Zero-Day appeared first on SecurityWeek.
پژوهشگران با صرف ۱.۲۱ میلیون دلار اعتبار هوش مصنوعی موفق شدند شیوه‌های بهره‌برداری جدیدی را در ایمن‌ترین بخش‌های هسته لینوکس بازسازی کنند. The post مدل سایبری OpenAI موفق به کشف ۹۴۸ آسیب‌پذیری در هسته لینوکس شد appeared first on دیجیاتو.
The large-scale watering hole campaign has been targeting entities in the US and Europe, mainly in Ukraine. The post Russia-Linked Hackers Hit iOS, Android Devices With Exploit Chains via Watering Holes appeared first on SecurityWeek.
Russia-linked group APT29 targeted iOS and Android users through hijacked websites and a compromised analytics service. Sekoia says a large-scale watering hole campaign is going after iOS and Android users, and it links the campaign to APT29 (aka SVR group, Cozy Bear, Nobelium, BlueBravo, Midnight Blizzard, and The Dukes), the Russian group tied to the SVR foreign intelligence service. A watering hole […]
