Firewall for AI
Firewall for AI
2026-09-03 归档
今日共收录 1407 条安全情报，包含 491 个 CVE，487 篇安全通告，以及 120 篇研究论文。
← 返回归档列表SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment
混合专家（Mixture-of-Experts, MoE）是一种用于大规模语言模型的缩放架构，每个token仅激活少量专家模块，从而在近乎恒定的计算量下实现参数规模的巨大增长。近期出现的混合MoE架构进一步引入了共享专家（shared ex
TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
这篇论文提出了一种针对检索增强生成（RAG）系统的知识投毒攻击防御框架。研究背景是：RAG通过外部语料库为大型语言模型提供事实依据，但系统对检索文档的隐式信任构成了严重攻击面。已有研究（如PoisonedRAG）表明，仅需少量精心构造的恶意
Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
该论文提出了一种基于知识图谱完成的技术，用于识别受到特定漏洞影响的库。问题背景是：广泛使用的第三方库存在漏洞时，可能影响数千甚至数百万的下游应用程序，但漏洞数据库（如 CVE 数据库）中往往存在缺失或错误的受影响库信息，超过一半的数据库条目
Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports
该论文针对威胁报告知识图谱提取工具评估的可复现性问题进行系统审计。研究者注意到工具发布时引用的三元组F1分数高度依赖于预测三元组与黄金标注之间的匹配规则，而匹配算法（精确匹配、同义词、嵌入相似度等）的选择会显著影响最终得分。作者检查了12个
NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing
本文针对先进制造业中日益复杂的网络物理攻击面与威胁情报分析难题，提出了一种基于图谱的神经符号推理框架 NeuroGraph。尽管大语言模型（LLM）与检索增强生成（RAG）已显著改善威胁情报工作流，但仍存在幻觉问题，并且难以对相互关联的威胁
OreProof: Verifiable Provenance with Limited Disclosure for Critical-Minerals Supply Chains Using Zero-Knowledge Proofs
本文报告了 OreProof 的设计科学实践：一个面向关键矿物（以黄金为实例）供应链的可追溯性平台原型。核心问题在于供应链中存在结构性矛盾：监管方和买家要求可验证的来源，而上游参与者不愿透露供应商身份、品位/产量和价格等敏感信息。OrePr
Under specific conditions, an attacker can register an attacker-controlled FIDO2 credential against a target account and then authenticate as that user. This issue affects on-pr...
CVE-2026-19117
根据NVD提供的CVE-2026-19117元数据，这是一个严重级别的身份认证绕过漏洞，CVSS基分为9.8，影响本地部署（on-premises）的产品，云服务版本不在影响范围。漏洞的核心在于攻击者在满足特定条件下，可以将自己控制的FID
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