MFSA 2026-65Security Vulnerabilities fixed in Firefox for iOS 152.3
MFSA 2026-65Security Vulnerabilities fixed in Firefox for iOS 152.3
2026-08-24 归档
今日共收录 798 条安全情报，包含 82 个 CVE，390 篇安全通告，以及 72 篇研究论文。
← 返回归档列表MFSA 2026-66Security Vulnerabilities fixed in Firefox for iOS 152.4
MFSA 2026-66Security Vulnerabilities fixed in Firefox for iOS 152.4
iOS 26.6 and iPadOS 26.6
iOS 26.6 and iPadOS 26.6
MFSA 2026-73Security Vulnerabilities fixed in Firefox for Android 153.0.3
MFSA 2026-73Security Vulnerabilities fixed in Firefox for Android 153.0.3
【大模型服务平台 TokenHub】&【智能体开发平台 ADP】&【云开发 CloudBase】关于腾讯云 DeepSeek-V4 正式版【原厂直供】模型计费调整通知
【大模型服务平台 TokenHub】&【智能体开发平台 ADP】&【云开发 CloudBase】关于腾讯云 DeepSeek-V4 正式版【原厂直供】模型计费调整通知
iOS 26.6.1 and iPadOS 26.6.1
iOS 26.6.1 and iPadOS 26.6.1
iOS 18.7.10 and iPadOS 18.7.10
iOS 18.7.10 and iPadOS 18.7.10
Firewall for AI
Firewall for AI
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
本文针对检索增强生成（RAG）系统中普遍存在的“安全-可靠性鸿沟”问题展开研究：RAG 将大语言模型（LLM）的输出锚定在外部知识上，但系统通常会无条件信任检索到的内容，导致高语义相关性并不等于事实真实性。攻击者可利用这一缺陷实施知识投毒，
$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN
本文针对开放、解聚的6G无线接入网（RAN）中多供应商共存场景下的安全与可信控制问题，提出了一种名为 $Z^2$-ACT（Zero-Knowledge Auditable Control and Zero-Trust Verifiable
Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making
本文研究大语言模型（LLM）在网络安全决策中的结构化推理能力，探讨其是真正具备安全推理还是依赖表面线索和先验知识。作者基于真实威胁场景（勒索软件、供应链攻陷、云滥用、Kubernetes 攻击、POS 恶意软件、ICS/OT 入侵）构建攻击
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
本文提出 AEGIS，一个针对 Model Context Protocol（MCP）的跨域资源滥用防护策略执行组件。MCP 是一种开源的 JSON-RPC 协议，用于标准化大语言模型（LLM）与外部系统之间通过工具（tools）进行的交互
TrustRAG: Blockchain-Enhanced RAG via Committee-Based Credibility Scoring
该论文提出 TrustRAG，一种基于委员会评分与区块链背书的新型检索增强生成（RAG）系统。传统 RAG 依赖集中式数据库，存在数据来源不明、内容被篡改、以及信任缺失等问题，尤其在医疗、金融、物流、法律等对信息时效性和准确性要求极高的领域
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