نبض سایبری اخبار امنیت سایبری، با ذکر منبع
EN
Check Point Blog

Audio Prompt Injection: What Voice Agents Hear That Text Guardrails Miss

Key takeaways Only 24 percent of organizations can fully inspect AI traffic without impacting performance, according to Check Point’s 2026 Cloud Security Report. →Voice agents are easy to talk into things. Researchers got a leading realtime voice model to give harmful answers to about 70 percent of spoken requests by varying their speed, pitch and background noise →A transcript check can be blinded. An attacker can s…

امنیت ابری امنیت هوش مصنوعی
خواندن متن کامل در Check Point 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 ←
The Hacker News

Chinese Hackers Use AI-Powered ARTEX to Target Over 200 Organizations Worldwide

Chinese state-sponsored threat actors have been observed using a Go-based artificial intelligence (AI)-powered penetration testing framework called ARTEX in attacks aimed at high-value targets simultaneously. The activity has been attributed by CrowdStrike to a China-based "targeted intrusion adversary" it tracks under the moniker Vapor Panda (previously VexatiousTemper). First identified in

امنیت هوش مصنوعی هوش مصنوعی و یادگیری ماشین تست نفوذ
منبع
دیجیاتو

مدیرعامل ابرآمد: هوش مصنوعی سازمانی با زیرساخت امن و پایدار ارزش می‌آفریند

گزارش دیجیاتو از سمینار «آینده زیرساخت سازمان» در «باهم ۱۴۰۵» را می‌توانید در ادامه مطالعه کنید. The post مدیرعامل ابرآمد: هوش مصنوعی سازمانی با زیرساخت امن و پایدار ارزش می‌آفریند appeared first on دیجیاتو.

امنیت هوش مصنوعی هوش مصنوعی و یادگیری ماشین
منبع
SecurityWeek

In Other News: Anthropic Breach Dispute, UEFI Flaw Hits Most Servers, Cloudflare AI Data Leak

Noteworthy stories that might have slipped under the radar: Iran eyed in military freezer hacks, Copenhagen University breach, AI-powered malware. The post In Other News: Anthropic Breach Dispute, UEFI Flaw Hits Most Servers, Cloudflare AI Data Leak appeared first on SecurityWeek.

بدافزار و آلودگی نشت داده امنیت هوش مصنوعی
منبع
SecurityWeek

Passkeys Are Better Than Passwords. But They Are Not Enough.

For decades, passwords have been one of cybersecurity’s most persistent weaknesses. Users forget them, reuse them, share them, and surrender them to convincing phishing sites. Attackers steal credentials, automate credential stuffing, and increasingly use artificial intelligence to make social engineering more effective. What are passkeys? Passkeys promise to eliminate much of this problem. Built on […] The post Pass…

فیشینگ امنیت هوش مصنوعی هوش مصنوعی و یادگیری ماشین
منبع