1
AI 加快漏洞发现，微软称 Win11 每月更新将整合更多安全修复
微软引入AI加速漏洞发现，Win11每月累积更新将整合更多安全修复，缩短从发现到防护的时间。
IT之家 7 月 10 日消息，微软昨日（7 月 9 日）发布博文，为适应 AI 推动的漏洞发现加速趋势，宣布调整 Windows 11 漏洞管理体系， 把 AI 引入漏洞发现、修复与验证流程，从而缩短从发现到防护的时间。 微软 Windows and Devices 执行副总裁帕万 · 达武鲁里（…
2
Show HN: 0day Rubbish – AI Vulnerability Discovery Platform (0day-Rubbish.com)
用多LLM集成发现Cisco CUCM 9.8级0day，含完整PoC与技术分析，展示AI驱动的漏洞挖掘新范式。
AI-driven platform using multi-LLM ensemble to discover and disclose critical 0-days. First case study: CVSS 9.8 unauthenticated RCE chain in Cisco CU…
3
SoK: AI-Augmented Binary Reversing
全面梳理AI如何革新二进制逆向分析，涵盖ML、LLM和智能代理的最新进展。
arXiv:2606.17398v1 Announce Type: cross Abstract: Binary reversing is fundamental to software understanding, vulnerability discovery, malware investig…
4
Hacking Salesforce Sites with an LLM Agent
LLM代理攻破Salesforce系统，揭秘10,000个漏洞背后的AI安全新挑战。
Article URL: https://www.reco.ai/blog/hacking-salesforce-sites-with-an-llm-agent Comments URL: https://news.ycombinator.com/item?id=48490289 Points: 2…
5
Frontier AI: what you need to know
英国家网络安全中心权威指南：前沿AI加速漏洞发现，解读组织如何提升安全基线应对网络攻防新态势
Article URL: https://www.ncsc.gov.uk/frontier-ai Comments URL: https://news.ycombinator.com/item?id=48481002 Points: 2 # Comments: 0
6
Show HN: GitHub Copilot port of Anthropic's AI vulnerability discovery harness
将 Anthropic 的 AI 漏洞发现工具移植到 GitHub Copilot CLI，让 Copilot 用户也能用上自主漏洞挖掘能力。
Last week, Anthropic released https://github.com/anthropics/defending-code-reference-harne... , a reference harness for autonomous vulnerability disco…
7
Anthropic's open-source framework for AI-powered vulnerability discovery
Anthropic开源AI漏洞发现框架，让自动化安全审计更强大。
Article URL: https://github.com/anthropics/defending-code-reference-harness Comments URL: https://news.ycombinator.com/item?id=48403980 Points: 16 # C…
8
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
用质量多样性进化算法系统性挖掘LLM安全漏洞，突破传统对抗测试的局限
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not…
9
Vulnerability report written by AI hacker agent
AI黑客代理270毫秒锁定OAuth端点漏洞，零权限确认8个高危漏洞，CVSS 8.7警告拉满！
Article URL: https://blog.tenzai.com/one-endpoint-zero-credentials-eight-confirmed-vulnerabilities/ Comments URL: https://news.ycombinator.com/item?id…