make smarter security investments and mitigate future risks
make smarter security investments and mitigate future risks
2026-09-05 归档
今日共收录 1726 条安全情报，包含 665 个 CVE，657 篇安全通告，以及 120 篇研究论文。
← 返回归档列表Inside Astaroth's New Spambot Component
Inside Astaroth's New Spambot Component
Falcon Platform IOAs Arrive in Falcon Next-Gen SIEM to Identify New Threats
Falcon Platform IOAs Arrive in Falcon Next-Gen SIEM to Identify New Threats
CrowdStrike 2026 Threat Hunting Report: Exploitation Window Closes as AI Use Accelerates
CrowdStrike 2026 Threat Hunting Report: Exploitation Window Closes as AI Use Accelerates
CrowdStrike Threat Hunts for Shell Command Obfuscation on VMware ESX
CrowdStrike Threat Hunts for Shell Command Obfuscation on VMware ESX
Google is a Leader in the IDC MarketScape: Worldwide Cybersecurity Consulting Services 2024 Vendor Assessment
Google is a Leader in the IDC MarketScape: Worldwide Cybersecurity Consulting Services 2024 Vendor Assessment
Teaching AI to Reason Through Detection Triage
Teaching AI to Reason Through Detection Triage
CrowdStrike Falcon Guardian Defines the Next Generation of AI SecuritySep 01, 2026
CrowdStrike Falcon Guardian Defines the Next Generation of AI SecuritySep 01, 2026
Peer Pressure: Inside the Sality Botnet Disruption Operation
Peer Pressure: Inside the Sality Botnet Disruption Operation
CrowdStrike Delivers the Next Evolution of the Agentic SOC
CrowdStrike Delivers the Next Evolution of the Agentic SOC
French hospital fined €500,000 after breach exposes data of 727,000
France's data protection authority (CNIL) has fined Hôpital privé de la Loire €500,000 ($580,000) for failing to adequat
HPE patches critical ArubaOS-CX remote code execution flaw
Hewlett Packard Enterprise (HPE) has patched a critical vulnerability in the ArubaOS-CX network operating system that co
Microsoft says some users can’t open the Teams desktop client
Microsoft is working to resolve a known issue that causes delays or blocks some users from opening the Microsoft Teams d
39 New Methods That Compromise Passkey Authentication
Passkeys eliminate many password-based attacks, but researchers have documented 39 methods for compromising authenticati
New CrowdStrike 'FalconFlank' zero-day grants SYSTEM privileges
An anonymous security researcher who uses the "Nightmare Eclipse" handle released a CrowdStrike Falcon zero-day exploit
Google warns of new Chrome zero-day flaw exploited in attacks
Google has updated the Chrome browser to address an actively exploited high-severity zero-day flaw in the V8 engine and
In Other News: Microsoft’s Cloud Patches, Hacked Dropbox Accounts, Guardio’s $1.1B Valuation
Noteworthy stories that might have slipped under the radar: Microsoft rolled out patches for cloud services, hackers com
Inferring Hidden User Models from the Behavior of Personalized LLM Agents
本文研究了个性化大语言模型（LLM）代理中的隐私泄露问题。近年来，个性化 LLM 代理会将用户记忆中保留的信息转换为压缩或结构化的表示，作者称之为“用户模型”，并以此指导后续决策。当源文本不在普通接口可访问的状态中时，这种用户模型通常被认为
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
该论文针对现代 AI Agent（智能体）框架的生命周期钩子（lifecycle hook）机制提出了一种新型供应链攻击面。此类钩子允许开发者将 shell 命令绑定到会话启动、工具调用、文件编辑等运行时事件上，并且这些命令以宿主机权限执行
The Implications of Linguistic Illegibility for LLM Security
该论文由 James Mickens 撰写，主题聚焦于大语言模型（LLM）的安全性，提出了一个核心概念：“linguistic illegibility”（语言不可读性）。论文指出，LLM 被训练用于生成自然语言，但多种证据表明，其外化的语