Beyond the Model: Harnessing Frontier AI for Stronger Cyber Defense
Beyond the Model: Harnessing Frontier AI for Stronger Cyber Defense
2026-08-23 归档
今日共收录 968 条安全情报，包含 250 个 CVE，385 篇安全通告，以及 68 篇研究论文。
← 返回归档列表make smarter security investments and mitigate future risks
make smarter security investments and mitigate future risks
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
August 2026 Patch Tuesday: One Exploited Zero-Day and 62 Critical Vulnerabilities Among 415 CVEsAug 11, 2026
August 2026 Patch Tuesday: One Exploited Zero-Day and 62 Critical Vulnerabilities Among 415 CVEsAug 11, 2026
Teaching AI to Reason Through Detection Triage
Teaching AI to Reason Through Detection Triage
Benchmaxxing: When the Benchmark Becomes the TargetAug 19, 2026
Benchmaxxing: When the Benchmark Becomes the TargetAug 19, 2026
New SynkLoader malware pushed in Microsoft Teams phishing campaign
A previously unknown malware family dubbed SynkLoader is being distributed in Microsoft Teams phishing campaigns to stea
Hundreds of leaked AWS keys give full control over corporate accounts
More than 9,300 Amazon Web Services (AWS) access keys publicly exposed between August 2022 and August 2026 are still act
Microsoft blames Windows gaming issues on RGB lighting devices
Microsoft says ongoing issues causing games to crash or fail to launch after installing the August 2026 Windows updates
Hackers infect Android car head units with proxy botnet malware
A supply-chain attack targeting Android-based car head units is using a legitimate device-update app to spread malware t
Named Pipes Under Attack: Securing Windows Interprocess Communication
Windows named pipes provide fast interprocess communication, but weak access controls can expose privileged services to
EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
这篇论文聚焦于大型推理模型（LRM）中隐藏思维链（Chain-of-Thought, CoT）的安全风险。当前前沿专有推理模型通常只向用户提供最终答案或简略摘要，完整的推理轨迹被视为核心资产且不公开。作者提出了一个核心研究问题：是否可以通过
Auditing Cross-Lingual Fairness in Language Model Watermarking
该论文针对大语言模型（LLM）输出水印方案在跨语言场景下的公平性评估缺失问题展开研究。目前，几乎所有水印方案的评估都仅基于英文文本，使用固定的检测阈值和狭窄的质量度量，忽略了多语言部署中因语言类型和书写系统差异带来的评估设计选择偏差。作者提
COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense
大型语言模型（LLM）容易受到提示注入攻击，攻击者将恶意指令嵌入用户输入或外部内容中，从而操纵模型行为并绕过安全防护。现有防御方法大多是静态的，依赖固定的对齐目标或特定于攻击的过滤机制，随着新攻击策略的出现需要重新设计。近期提出的终身对齐方
From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs
本文针对安全日志异常检测中现有方法的不足开展研究。传统基于规则的检测系统（如Wazuh）依赖预定义规则，难以应对未知或变体攻击；而统计异常检测方法（如OpenSearch）仅能识别与历史行为模式的偏差，缺乏对语义和上下文的深入理解。近年来，
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
本文提出 MaliciousSkillBench，一个针对恶意 Agent Skill 检测的综合基准。Agent Skills 为 LLM 智能体提供了可复用的指令包，其中可能包含脚本、资源和服务配置，这为恶意行为提供了直接的分发渠道。然