2026-07-15 归档

今日共收录 995 条安全情报,包含 81 个 CVE,528 篇安全通告,以及 87 篇研究论文。

← 返回归档列表
学术论文2026-07-13 发布INFO

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

该论文揭示了多智能体、工具调用LLM系统在安全监控中的一个根本缺陷:传统的运行时监视器对每个消息、工具调用或步骤进行独立检查,但分布式后门攻击将有害负载拆分成多个片段分配到不同智能体上,使得每个局部检查都看似正常,而组装后的整体却构成攻击。

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-07-13 发布INFO

LLM-Guided Program Evolution for Targeted Black-Box Attacks on Perceptual Hash Algorithms

感知哈希算法(PHA)广泛应用于图像篡改检测,但其在对抗性扰动下的鲁棒性尚未得到充分研究。本文提出一种基于进化框架(GigaEvo和OpenEvolve)的新型黑盒攻击方法,针对感知哈希算法实施目标性二次图像攻击。攻击性能通过复合评分衡量,

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-07-11 发布INFO

Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge

本文研究了大语言模型(LLM)内部如何识别恶意代码的机制。尽管LLM在代码补全、漏洞检测等软件工程任务中表现优异,但其识别恶意或漏洞代码的内部工作机制仍不透明。作者采用机械可解释性方法,对三个指令微调的LLM(Llama3.1-8B-Ins

历史摘要 · 未重新核验 · arXiv cs.CR

学术论文2026-07-11 发布INFO

Firewall3D: A Hardware Firewall for Defending 3D Printers Against Firmware Attacks

随着3D打印市场快速增长(估值超过300亿美元),针对增材制造系统的网络安全风险也在上升。攻击者可能破坏打印部件、窃取知识产权,甚至物理损坏3D打印机。固件级攻击是主要威胁之一,可通过供应链入侵、恶意固件更新或内部威胁引入,从而操纵打印机行

历史摘要 · 未重新核验 · arXiv cs.CR

漏洞预警2026-07-13 发布CRITICAL

Crypt::OpenSSL::X509 versions before 2.1.3 for Perl allow a heap out-of-bounds read via a long certificate extension OID in hv_exts. When building the extension hash (via exten...

CVE-2026-58102

Crypt::OpenSSL::X509 是一个 Perl 模块,用于处理 X.509 证书。在版本 2.1.3 之前,该模块存在一个堆越界读取漏洞。当使用 extensions()、extensions_by_long_name()、ex

历史摘要 · 未重新核验 · NVD

学术论文2026-07-12 发布INFO

PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference

PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference

历史摘要 · 未重新核验 · arXiv cs.CR

安全公告2026-07-14 发布INFO

Ech0: ParseAcceptLanguage `_` separator bypass enables ~70x CPU amplification via Accept-Language header in i18n.Middleware

### Summary Ech0's i18n middleware runs on every HTTP request and constructs a fresh `*goi18n.Localizer` from the raw `

历史摘要 · 未重新核验 · GitHub Advisory

威胁情报2026-07-15 发布INFO

Cloud & Application Security

Cloud & Application Security

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-15 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2026-07-15 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2026-07-15 发布INFO

CrowdStrike Named an Innovation and Growth Leader in the 2026 Frost Radar™: Cloud and Application Runtime Security

CrowdStrike Named an Innovation and Growth Leader in the 2026 Frost Radar™: Cloud and Application Runtime Security

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-15 发布INFO

CrowdStrike Expands Identity Leadership with OpenID and IDPro

CrowdStrike Expands Identity Leadership with OpenID and IDPro

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-15 发布INFO

cloud architecture assessment

cloud architecture assessment

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-07-15 发布INFO

ransomware and multifaceted extortion defense

ransomware and multifaceted extortion defense

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-07-15 发布INFO

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

历史摘要 · 未重新核验 · Mandiant

威胁情报2026-07-15 发布INFO

The Identity Problem Hiding in AI Agent Deployments

The Identity Problem Hiding in AI Agent Deployments

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-15 发布INFO

94% of Organizations Report Cloud Breaches: CrowdStrike State of CDR Survey

94% of Organizations Report Cloud Breaches: CrowdStrike State of CDR Survey

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-15 发布INFO

Falcon Cloud Security June 2026 Release: Updates for Azure and Google Cloud

Falcon Cloud Security June 2026 Release: Updates for Azure and Google Cloud

历史摘要 · 未重新核验 · CrowdStrike

威胁情报2026-07-13 发布INFO

Defending SaaS-based applications against ShinyHunters OAuth abuse

Microsoft Threat Intelligence identified threat actor activity with overlapping tradecraft commonly associated with Shin

历史摘要 · 未重新核验 · Microsoft Threat Intelligence

威胁情报2026-07-14 发布INFO

Microsoft Entra ID gets passkeys default authentication starting September

Microsoft has announced that passkeys will become the default authentication method for the Entra ID enterprise identity

历史摘要 · 未重新核验 · BleepingComputer