AI agent security now has a purpose-built open-source guardrail: Ant Group released SingGuard-NSFA, a free framework that catches prompt injection and credential-theft patterns before AI agents ...
2 天
黑马程序员老师直接接听
10 多年项目研发与教学经验，曾在汇丰银行等多家企业担任研发工程师，精通 Java EE 体系技术，包括 SpringBoot、SpringCloud、MySQL、Redis、MQ 等技术及分布式解决方案有深入研究。不断探索 AI 前沿新技术，对于 ...
An exposed attack server led Lexfo to three Microsoft 365 phishing operations using Evilginx and device code abuse to capture ...
a laptop screen with a webpage of the IT Army of Ukraine group of volunteer hackers. The IT Army of Ukraine first set up in the wake of Russia's devastating attack, and has since hugely grown in ...
Sysdig says JADEPUFFER may be the first agentic ransomware case, exposing how AI agents can turn old credential failures into database destruction. JADEPUFFER is a warning about exposed AI ...
An "agentic threat actor" successfully exploited a Langflow flaw to steal data from a production database server and encrypt ...
13 天on MSN
全球首例!AI Agent自主完成勒索攻击全流程，企业安全防护面临新挑战
安全研究机构 Sysdig 发布报告称，其威胁研究团队发现全球首例完全由 AI 智能体自主执行的勒索软件攻击事件。该攻击被命名为 JADEPUFFER，其显著特征在于全程无需人类干预，即可完成从系统入侵到数据摧毁的完整攻击链路。 攻击溯源显示，初始突破口为一台暴露在公网的 Langflow 服务。攻击者利用 CVE-2025-3248 ...
Attackers exploited Langflow vulnerability CVE-2025-3248 to conduct an agentic AI-powered ransomware attack involving reconnaissance, credential theft, and lateral movement.
CNMO科技 on MSN
全球首例AI代理勒索攻击被发现 可完成完整攻击链路
【CNMO科技消息】据CNMO科技了解，安全厂商Sysdig的研究人员近日记录到全球首个完全由AI代理自动执行的勒索软件攻击，该攻击程序被命名为JadePuffer。目前该攻击已证实可完成完整的攻击链路，意味着AI代理技术已被网络犯罪团伙投入实际应用 ...
Data scientists play a crucial role in helping people and organizations use data to make more informed decisions. Since they ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果