Firewall for AI
该来源是 Akamai 官方发布的产品页面，介绍其面向人工智能应用的新型安全防护产品 'Firewall for AI'（AI 防火墙）。该产品定位为保护 AI 基础设施和 AI 驱动的应用程序免受各类网络攻击，尤其是 DDoS（分布式拒绝
2026-08-30 归档
今日共收录 849 条安全情报，包含 76 个 CVE，428 篇安全通告，以及 85 篇研究论文。
← 返回归档列表Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation
该论文针对大语言模型（LLM）生成的寄存器传输级（RTL）代码的安全性展开研究。与软件代码不同，RTL 代码一旦流片（tape-out）到硅片上便无法修补安全漏洞，因此其安全性至关重要。现有研究主要关注 LLM 生成软件代码的安全问题，而
PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?
PLCBench 是一篇来自工业控制系统安全领域的研究论文，针对大型语言模型（LLM）智能体在工业控制系统中可能构成的网络-物理攻击威胁。传统 ICS 依赖 PLC 将网络计算与物理控制连接，而具备工具使用能力的自主 LLM 智能体能否将可
SPA: Securing Persistent LLM Agents Across Queries with Plan-First Information-Flow Control
本文提出 SPA（Plan-First Information-Flow Control），一种保护持久化 LLM 智能体跨查询安全的架构。随着 LLM 智能体越来越常操作不可信网页、文档、工具及持久状态，同时掌握敏感资源权限，攻击者注入的
Five Primitives for Governing Autonomous AI Agents at Runtime
本文针对企业环境中自主AI智能体（autonomous AI agents）的运行时治理问题，提出了一套由五个原语（primitives）构成的治理框架。作者指出，当前为人类用户和长期运行服务设计的控制模型，在应对AI智能体时存在三类结构性
RTLGuard: A Lightweight Teacher-Student Defense for Poisoned RTL Code Generation Models
随着大语言模型（LLM）在硬件设计领域的应用，寄存器传输级（RTL）代码的自动化生成成为趋势，设计者可以利用LLM将高层级规范转换为可综合的硬件描述。然而，这类模型通常基于第三方预训练模型进行微调，其训练数据和适配过程不透明，导致供应链中存
MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
本文针对大型语言模型（LLM）在代码生成任务中虽然能实现功能正确性，却常常产生包含安全漏洞的代码这一问题，提出了一种基于多智能体协作的代码生成框架 MACGen。作者指出，安全代码生成本质上是一个多目标优化问题，需要同时兼顾功能正确性与安全
The MyHome Core plugin for WordPress is vulnerable to Authentication Bypass in all versions up to, and including, 4.4.5. This is due to missing authorization in the send_link() ...
CVE-2026-15980
CVE-2026-15980 是 MyHome Core WordPress 插件中的一个高危身份验证绕过漏洞，影响所有版本直至并包括 4.4.5。漏洞根因在于 send_link() AJAX 处理器缺少权限检查，以及 activate(
The Custom User Registration Fields for WooCommerce plugin for WordPress is vulnerable to Privilege Escalation in versions up to, and including, 2.2.3. This is due to the plugin...
CVE-2026-15369
该漏洞影响WordPress插件Custom User Registration Fields for WooCommerce，版本至2.2.3（含）。插件在结账流程中存在权限提升漏洞。具体地，在af_reg_checkout_data_t
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