Extracting Knowledge from Tools in LLM Agents
该论文研究了大语言模型（LLM）智能体在使用知识型工具过程中的安全风险。LLM智能体通过工具调用访问底层文件、数据库和搜索索引，以增强领域服务能力，但同时也引入了工具介导的知识提取攻击面：攻击者可以通过精心设计的输出来逐步恢复目标工具背后的
2026-09-01 归档
今日共收录 1266 条安全情报，包含 424 个 CVE，451 篇安全通告，以及 107 篇研究论文。
← 返回归档列表Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
本文研究云-边协同解码范式中的隐私泄露问题。在该范式下，资源受限的边缘设备持有私有数据，并运行一个小语言模型（SLM）生成下一token分布；云端LLM仅基于公开数据进行预测；两者分布融合后生成最终输出。这种设计旨在避免将私有数据直接上传至
BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence
本文提出 BEACON，一个基于 LLM 的跨来源网络威胁情报（CTI）知识图谱自动构建框架。研究背景是：大量 CTI 以非结构化报告形式存在，数量庞大且异构性强，人工分析难以应对；现有自动构建知识图谱的方法大多只处理单篇报告的部分信息，未
LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
本文是一篇系统文献综述，聚焦于基于大型语言模型（LLM）的智能体（Agent）在软件与系统安全领域中的应用。研究背景是：安全分析工作往往依赖程序化流程，分析师需要检查异构工件、形成假设、调用工具、解读输出并修订计划。LLM智能体具备规划、工
Cloud & Application Security
Cloud & Application Security
From Scanner to Stealer: Inside the trivy-action Supply Chain Compromise
From Scanner to Stealer: Inside the trivy-action Supply Chain Compromise
Next-Gen Identity Security
Next-Gen Identity Security
CrowdStrike Expands Identity Leadership with OpenID and IDPro
CrowdStrike Expands Identity Leadership with OpenID and IDPro
cloud architecture assessment
cloud architecture assessment
ransomware and multifaceted extortion defense
ransomware and multifaceted extortion defense
Google Cloud Next 2026Catch-up sessions on the keynotes and select sessions are now available on demand.Explore content on-demand
Google Cloud Next 2026Catch-up sessions on the keynotes and select sessions are now available on demand.Explore content
The Identity Problem Hiding in AI Agent Deployments
The Identity Problem Hiding in AI Agent Deployments
94% of Organizations Report Cloud Breaches: CrowdStrike State of CDR Survey
94% of Organizations Report Cloud Breaches: CrowdStrike State of CDR Survey
Falcon Cloud Security June 2026 Release: Updates for Azure and Google Cloud
Falcon Cloud Security June 2026 Release: Updates for Azure and Google Cloud
Falcon Cloud Security July 2026 Release: Helping Security Teams Move Faster in the Cloud
Falcon Cloud Security July 2026 Release: Helping Security Teams Move Faster in the Cloud
CrowdStrike Named Strongest Overall Leader in 2026 Frost Radar™: Cloud Workload Protection Platforms
CrowdStrike Named Strongest Overall Leader in 2026 Frost Radar™: Cloud Workload Protection Platforms
Aurora Ransomware Operators Use Cursor AI in Attacks Against 10 Targets
Threat actors associated with Aurora (aka Aur0ra) ransomware have been observed using SpaceX's artificial intelligence (
Spectre Declassified: Reading from the Right Place at the Wrong Time.
该论文研究推测执行（speculative execution）与信息流语言中“去分类”（declassify）机制之间的相互作用。在实用的信息流编程语言中，程序员可通过 declassify 构造声明有意泄露的数据，例如从私钥计算出的签名
Injection Attacks Reloaded: Tunnelling Malicious Payloads over DNS.
该论文揭示了一个由DNS协议设计原则引发的严重安全问题。传统互联网协议设计原则要求“发送时严格，接收时宽容”，DNS也不例外。为了支持新应用，DNS被设计为透明处理各类记录类型（RFC3597），即任何应用只需创建新的DNS记录，即可通过现
Practical Timing Side-Channel Attacks on Memory Compression.
本文首次提出并系统研究了内存压缩算法中的时序侧信道攻击，命名为 Decomp+Time。此前针对压缩算法的侧信道研究仅利用了压缩率（如压缩后数据大小）这一指标，而本文发现解压过程中的数据依赖操作也会引入可观测的时序差异，从而构成信息泄露通道