iOS 18.7 and iPadOS 18.7
iOS 18.7 and iPadOS 18.7
2026-06-13 归档
今日共收录 1165 条安全情报，包含 370 个 CVE，402 篇安全通告，以及 115 篇研究论文。
← 返回归档列表Android Code Search
Android Code Search
Android Devices
Android Devices
Secure an Android device
Secure an Android device
Android 16 QPR2
Android 16 QPR2
Mobile network security
Mobile network security
iOS 26.5 and iPadOS 26.5
iOS 26.5 and iPadOS 26.5
iOS 18.7.9 and iPadOS 18.7.9
iOS 18.7.9 and iPadOS 18.7.9
iOS 16.7.16 and iPadOS 16.7.16
iOS 16.7.16 and iPadOS 16.7.16
iOS 15.8.8 and iPadOS 15.8.8
iOS 15.8.8 and iPadOS 15.8.8
MFSA 2026-49Security Vulnerabilities fixed in Firefox for iOS 151.0
MFSA 2026-49Security Vulnerabilities fixed in Firefox for iOS 151.0
MFSA 2026-52Security Vulnerabilities fixed in Firefox for iOS 151.1
MFSA 2026-52Security Vulnerabilities fixed in Firefox for iOS 151.1
MFSA 2026-53Security Vulnerabilities fixed in Firefox for iOS 151.2
MFSA 2026-53Security Vulnerabilities fixed in Firefox for iOS 151.2
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
Stable Channel Update for ChromeOS / ChromeOS Flex
M-148, ChromeOS version 16640.61.0 (Browser version 148.0.7778.263) has rolled out to ChromeOS devices on the Stable cha
Chrome for Android Update
Hi, everyone! We've just released Chrome 149 (149.0.7827.114) for Android. It'll become available on Google Play over th
Beta Channel Update for ChromeOS / ChromeOS Flex
The ChromeOS Beta channel is being updated to OS version 16667.40.0 (Browser version 149.0.7827.136) for most ChromeOS d
The Emergence of Autonomous Penetration Capabilities in Large Language Model-Powered AI Systems
本文针对当前大语言模型（LLM）驱动的AI系统自主渗透能力评估中存在的局限性，提出了一种新的自主渗透评估框架。现有评估方法存在方法论不透明、测试场景不现实、给予LLM过多先验知识和任务指导等问题，无法准确反映现代AI系统在高影响网络攻击场景
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems
该论文聚焦于持久性 LLM 代理系统中的多会话记忆投毒（MSMP）攻击及防御。随着检索增强生成（RAG）代理广泛使用跨用户会话累积的持久记忆，攻击者可通过正常交互注入精心构造的记忆，当这些记忆被后续用户检索时，可操纵代理的响应，而无需修改模
OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
该论文提出 OCELOT，一种用于保护 LLM Agent 隐私的运行时中介系统。LLM Agent 在执行用户任务时，需要读取个人文件、调用工具、与外部服务交互，这可能导致个人身份信息（PII）在多个信任边界间泄露。隐私问题在这里具有三个