MFSA 2026-53Security Vulnerabilities fixed in Firefox for iOS 151.2
MFSA 2026-53Security Vulnerabilities fixed in Firefox for iOS 151.2
2026-07-09 归档
今日共收录 1410 条安全情报，包含 455 个 CVE，561 篇安全通告，以及 105 篇研究论文。
← 返回归档列表MFSA 2026-55Security Vulnerabilities fixed in Focus for iOS / Klar 151.3.1
MFSA 2026-55Security Vulnerabilities fixed in Focus for iOS / Klar 151.3.1
MFSA 2026-56Security Vulnerabilities fixed in Firefox for iOS 152.0
MFSA 2026-56Security Vulnerabilities fixed in Firefox for iOS 152.0
【Cloud Mate】产品退市及停止服务公告
【Cloud Mate】产品退市及停止服务公告
iOS 26.5.2 and iPadOS 26.5.2
iOS 26.5.2 and iPadOS 26.5.2
MFSA 2026-65Security Vulnerabilities fixed in Firefox for iOS 152.3
MFSA 2026-65Security Vulnerabilities fixed in Firefox for iOS 152.3
Dev Channel Update for ChromeOS / ChromeOS Flex
The ChromeOS Dev channel is being updated to OS version 16733.12.0 (Browser version 151.0.7922.14) for most ChromeOS de
【大模型服务平台 TokenHub】&【智能体开发平台】& 【云开发 CloudBase】 关于腾讯云 MiniMax-M2.5 模型下线及切换升级的通知
【大模型服务平台 TokenHub】&【智能体开发平台】& 【云开发 CloudBase】 关于腾讯云 MiniMax-M2.5 模型下线及切换升级的通知
Chrome for Android Update
Hi, everyone! We've just released Chrome 150 (150.0.7871.114) for Android. It'll become available on Google Play over
Chrome Stable for iOS Update
Hi everyone! We've just released Chrome Stable 150 (150.0.7871.113) for iOS; it'll become available on App Store in the
PAN-SA-2026-0010 Chromium and Prisma Browser: Monthly Vulnerability Update (July 2026) (Severity: HIGH)
PAN-SA-2026-0010 Chromium and Prisma Browser: Monthly Vulnerability Update (July 2026) (Severity: HIGH)
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
本文提出了一种针对大型语言模型（LLM）智能体持久记忆的新型攻击方法——伪造放大推理记忆攻击（FARMA）。传统的记忆中毒攻击主要污染事实性知识，而FARMA则针对智能体的推理历史进行注入。攻击者通过插入含有规避性语言的伪造推理痕迹，绕过基
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
该论文研究多模态大语言模型（MLLMs）中机器遗忘（MMU）的鲁棒性问题。MLLMs在跨模态任务中表现优异，但可能无意中编码隐私敏感信息，引发隐私或版权侵犯担忧。MMU作为一种缓解方法被提出，旨在强制模型遗忘私有信息。然而，当模型发布并被恶
ECO/CPO-DAG: A Contradiction-Based Accountability Layer for Adversarial Supply Chains
该论文提出ECO/CPO-DAG，一个针对对抗性供应链的领域特定问责协议，将矛盾检测形式化为一个补充性的验证层，而非共识或真理建立机制。参与者将签名的事件声明对象（ECO）发布到一个因果有序、仅追加的有向无环图（DAG）中，其边编码了“发生
Context-to-Execution Integrity for LLM Agents
本文提出了面向LLM智能体的上下文到执行完整性（Context-to-Execution Integrity, CXI）系统。LLM智能体在执行任务时，通常需要读取攻击者可写入的上下文，并调用工具。现有系统缺乏对工具调用中敏感字段（prot
Code-Level Cost Function Generation for Spatial Image Steganography Using RAG-Enhanced Large Language Models
本文针对自适应隐写术中代价函数设计通常依赖人工调参或深度学习黑盒的问题，提出了一种基于检索增强生成（RAG）增强的大语言模型（LLM）的自动代码级空间图像隐写代价函数生成系统。系统核心是自进化RAG（SE-RAG）模块，其中代码语义签名（C
TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction
网络威胁情报（CTI）报告通常是非结构化、异构且包含噪声的，这限制了它们在自动化分析与推理中的直接可用性。网络安全知识图谱（CSKG）能够以结构化形式表示攻击实体、行动和关系，但从自由文本CTI中构建此类图谱仍然是一个挑战。现有方法通常依赖
Improper neutralization of input during web page generation ('cross-site scripting') in Dynamics 365 Customer Voice allows an unauthorized attacker to perform spoofing over a ne...
CVE-2026-47646
该漏洞（CVE-2026-47646）存在于 Microsoft Dynamics 365 Customer Voice 中，属于跨站脚本（XSS）类型。由于网页生成过程中对用户输入进行了不恰当的清理，未授权的远程攻击者能够通过网络向目标用
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