2026-05-27 归档

今日共收录 1142 条安全情报,包含 375 个 CVE,381 篇安全通告,以及 103 篇研究论文。

← 返回归档列表
学术论文2026-05-26 发布INFO

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

该论文研究了大型语言模型(LLM)概念消除中的反事实微调(CFT)范式。CFT通过训练模型生成替代的虚构知识来替代不需要的内容,是一种有前景的方法。然而,作者发现CFT在某些方面仍不如其他范式,并揭示了两个被忽视的问题:(1)知识冲突:反事

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-05-26 发布INFO

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

该论文针对开放权重大语言模型(LLM)的微调防护机制进行了系统性研究。现有防护假设有害行为只能通过微调习得,但论文指出预训练模型已蕴含大量有害知识,因此攻击者可能无需微调,仅通过越狱手段即可绕过防护。作者评估了两种低成本攻击方法:ablit

历史摘要 · 未重新核验 · arXiv cs.CR

威胁情报2026-05-27 发布INFO

CrowdStrike Named a Leader in Frost & Sullivan 2026 Radar for Cloud-Native Application Protection Platforms

CrowdStrike Named a Leader in Frost & Sullivan 2026 Radar for Cloud-Native Application Protection Platforms

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

CrowdStrike Expands Real-Time Cloud Detection and Response to Google Cloud

CrowdStrike Expands Real-Time Cloud Detection and Response to Google Cloud

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

CrowdStrike Falcon Cloud Security Delivered 264% ROI Through Unified Cloud Protection

CrowdStrike Falcon Cloud Security Delivered 264% ROI Through Unified Cloud Protection

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

Security & Identity

Security & Identity

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

SAP on Google Cloud

SAP on Google Cloud

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Inside Google Cloud

Inside Google Cloud

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Google Cloud Next & Events

Google Cloud Next & Events

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Google Cloud Consulting

Google Cloud Consulting

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Transform with Google Cloud

Transform with Google Cloud

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Threat IntelligenceNorth Korea-Nexus Threat Actor Compromises Widely Used Axios NPM Package in Supply Chain AttackBy Google Threat Intelligence Group • 16-minute read

Threat IntelligenceNorth Korea-Nexus Threat Actor Compromises Widely Used Axios NPM Package in Supply Chain AttackBy Goo

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Google Cloud Products

Google Cloud Products

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-05-27 发布INFO

Cloud & Application Security

Cloud & Application Security

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

From Scanner to Stealer: Inside the trivy-action Supply Chain Compromise

From Scanner to Stealer: Inside the trivy-action Supply Chain Compromise

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

Next-Gen Identity Security

Next-Gen Identity Security

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

CrowdStrike FalconID Brings Phishing-Resistant MFA to Falcon Next-Gen Identity Security

CrowdStrike FalconID Brings Phishing-Resistant MFA to Falcon Next-Gen Identity Security

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-27 发布INFO

CrowdStrike Named a Leader in Identity Threat Detection and Response

CrowdStrike Named a Leader in Identity Threat Detection and Response

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-05-26 发布INFO

Iranian APT Targets Aviation, Software Companies With Updated Tools

Nimbus Manticore has continued its operations during and after the US military campaign against Iran. The post Iranian A

历史摘要 · 未重新核验 · SecurityWeek

学术论文2026-05-25 发布INFO

FuzzPilot: Plateau-Triggered Recipe Validation for Structured Text Fuzzing

FuzzPilot 是一个针对 AFL++ 模糊测试工具的控制器,旨在解决结构化文本(如 JSON、XML)模糊测试中的覆盖率平台期问题。传统上,AFL++ 的突变热路径中会执行昂贵的推理操作(如语法分析、语义验证),导致性能瓶颈。Fuzz

历史摘要 · 未重新核验 · arXiv cs.CR