Trained to betray: How post-training supply chain attacks hijack coding agents

Microsoft Defender Research and the AI Red Team discuss how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities. The post Trained to betray: How post-training supply chain attacks hijack coding agents appeared first on Microsoft Security Blog.

بدافزار و آلودگی آسیب‌پذیری و روز صفر امنیت هوش مصنوعی امنیت زنجیره تأمین هوش تهدید متن‌باز پاسخ به رخداد و جرم‌یابی تست نفوذ امنیت هویت و دسترسی
خواندن متن کامل در Microsoft Security Blog درخواست حذف

این صفحه فقط عنوان و خلاصه کوتاه خبر را نمایش می‌دهد. متن کامل در منبع اصلی منتشر شده است.

خبرهای مرتبط

آرشیو کامل ←
CERT-EU

2026-020: Critical Vulnerabilities in Citrix NetScaler ADC and NetScaler Gateway

On 12 November 2026, the Cloud Software Group published security bulletins for its Citrix products addressing 28 memory flaws in Citrix NetScaler ADC and Citrix NetScaler Gateway. One of these vulnerabilities, CVE-2026-120868, affects every deployment, including those using the default configuration. The vendor bulletin describes the impact as unpredictable behaviour and denial of service. Citrix reports no exploitat…

CERT/CC Vulnerability Notes

VU#580079: Arbitrary file read/write vulnerability in ImageMagick-based applications with default configuration

Overview Multiple arbitrary file read and write vulnerabilities have been identified in applications that use ImageMagick with insufficiently restrictive security policies. Collectively referred to as ImageTragick2, these issues arise when ImageMagick processes attacker-controlled SVG or PostScript content using dangerous coders or delegates permitted by its default or application-supplied configuration. An attacker…