Anthropic takes risky AI tests offline after models breach govt sites
Anthropic announced that its internal AI models undergoing "high-risk and cybersecurity evaluations" no longer have inte
2026-10-13 归档
今日共收录 1460 条安全情报，包含 709 个 CVE，466 篇安全通告，以及 13 篇研究论文。
← 返回归档列表Cyberattack shuts down refrigerators at French supermarkets
Attackers remotely defrosted refrigerators at multiple French supermarket chains overnight in a cyberattack that reporte
Inside AvisLoader: A Windows Malware Loader Built to Resist Disruption
A new Windows malware loader called AvisLoader uses encrypted peer-to-peer communications to make command-and-control in
Retail giant Ahold Delhaize takes systems offline after cyberattack
Retail giant Ahold Delhaize, one of the world's largest food retail chains, confirmed today that it had to take some sys
GitLab warns of max severity code execution vulnerability
GitLab warned users today to immediately patch a maximum-severity vulnerability in the CI/CD Regular Expression Compiler
Microsoft: Windows 11 23H2 reaches end of support in 30 days
Microsoft has reminded customers that systems running Windows 11 23H2 Enterprise, Education, and IoT Enterprise editions
⚡ Weekly Recap: Helpdesk 0-Days, Rogue Certs, ShinyHunters Arrest, AI-Fooling Malware and More
Some meetings last longer than it took attackers to jump on a newly disclosed security flaw this week. Within hours, the
Ransomware Response Expert Arrested in ShinyHunters FBI Hack Probe
The suspect is believed to be Edward Dubrovsky, a Canadian cybersecurity executive who was visiting the United States fo
ToFu: Exploiting and Fuzzing the LLM-Orchestrator-Tool Trust Boundary
Large language models (LLMs) are increasingly deployed as agents that interact with external software through tools, wit
EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair
Recent advances in large language models (LLMs) have enabled agent-based approaches for repository-level automated vulne
Understanding Verification Vulnerabilities in Cross-chain Bridges: An Empirical Study
With the rapid development of blockchain technology, numerous heterogeneous blockchains have emerged, each featuring dis
[原创] 别傻了，你的引擎加密挡不住"不讲武德"的邪修 —— XA 内存盲打补丁，记偏移秒改的实战套路
[原创] 别傻了，你的引擎加密挡不住"不讲武德"的邪修 —— XA 内存盲打补丁，记偏移秒改的实战套路
[原创]IDAPro v9.4.260714 汉化补丁修正错误
[原创]IDAPro v9.4.260714 汉化补丁修正错误
[原创]CVE-2020-6507利用链
CVE-2020-6507
[原创]CVE-2020-6507利用链
CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报
CVE-2026-39821
CVE-2026-39821：Go idna 纯 ASCII 标签解码漏报
Critical SonicWall SMA 1000 Flaw Targeted in 135 Exploitation Attempts After Patch
CVE-2026-102255
Threat actors have been observed exploiting a recently disclosed critical security flaw in SonicWall Secure Mobile Acces
Attackers Exploit CVSS 10.0 Bricksforge WordPress Flaw Enabling Unauthenticated RCE
CVE-2026-85097
A maximum-severity security flaw impacting the Bricksforge plugin for WordPress has come under active exploitation in th
Bricksforge WordPress Plugin Vulnerability Exploited in the Wild
CVE-2026-85097
The vulnerability tracked as CVE-2026-85097 can allow threat actors to take control of the targeted WordPress websites.
Critical SonicWall Vulnerability Exploited Days After Disclosure
CVE-2026-102255
CVE-2026-102255 is a pre-authenticated SSRF flaw that could allow attackers to perform unauthorized operations. The post
AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the