[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-security":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"476981b3-af8a-4cef-8dce-e66bf3126a81","AI security","ai-security",12,"AI security 聚焦模型、應用與基礎設施的風險管理，從 jailbreak、提示注入、資料外洩到自動化漏洞偵測都涵蓋在內。對開發者而言，它關乎模型上線前的評估、權限邊界與攻擊面控制。","AI security covers the risks around models, apps, and infrastructure: jailbreaks, prompt injection, data leakage, and automated vulnerability testing. For developers, it matters because deployment now depends on clear evaluation, permission boundaries, and attack-surface control.",[12,21,29,37,44,52,60,67,74,82,89,96,103,110,117,124,131,138,145],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"719e91f4-4f53-4dd2-a1e6-3f6440226425","ibm-red-hat-5b-open-source-ai-security-en","IBM, Red Hat pledge $5B for open source AI security","IBM and Red Hat are launching Project Lightwell, a $5 billion push to secure open source software with AI and 20,000 engineers.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780257774949-3gqn.png","en","2026-05-31T20:02:27.249878+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"c25cb6d2-274f-439c-8569-ce92f9533e5c","how-to-secure-ai-assistants-end-to-end-en","How to Secure AI Assistants End to End","Set up data-layer controls, encryption, and audit logs to reduce AI assistant security risk.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779983283626-3sqk.png","2026-05-28T15:47:27.371555+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":34,"image_url":35,"cover_image":35,"language":19,"created_at":36},"8c034017-69a3-4b32-8279-4fc52bfa5218","ibm-anthropic-ai-security-project-glasswing-en","IBM adds Anthropic-backed AI security push","IBM expanded AI security services and teamed with Anthropic on Project Glasswing to help secure open-source software in critical infrastructure.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779408353661-i3ne.png","2026-05-22T00:05:28.945766+00:00",{"id":38,"slug":39,"title":40,"summary":41,"category":26,"image_url":42,"cover_image":42,"language":19,"created_at":43},"3a352268-d5bf-423e-98dc-b3fbfe4add43","agentic-ai-turns-autonomy-into-security-problem-en","Agentic AI turns autonomy into a security problem","A developer’s breakdown of Forbes’ agentic AI hub, with a copy-ready governance template for agents, drift, and authority control.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779139471362-dv7k.png","2026-05-18T21:24:05.681031+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":49,"image_url":50,"cover_image":50,"language":19,"created_at":51},"94f7efad-6f63-4873-9d18-62267154c2c7","microsoft-mdash-finds-16-windows-flaws-en","Microsoft’s MDASH finds 16 Windows flaws","Microsoft’s MDASH AI found 16 Windows flaws, including four critical RCEs, and will enter private preview for enterprises in June.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779041042789-ijfw.png","2026-05-17T18:03:36.342551+00:00",{"id":53,"slug":54,"title":55,"summary":56,"category":57,"image_url":58,"cover_image":58,"language":19,"created_at":59},"9bbe48b2-19ad-4bbf-bb20-af02e7d15a03","yakovenko-warns-ai-could-crack-pqc-wallets-en","Yakovenko Warns AI Could Crack PQC Wallets","Solana co-founder Anatoly Yakovenko says AI may break post-quantum signature schemes before blockchains finish migrating.","blockchain","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778170258841-108q.png","2026-05-07T16:10:42.813868+00:00",{"id":61,"slug":62,"title":63,"summary":64,"category":49,"image_url":65,"cover_image":65,"language":19,"created_at":66},"c5b33206-47f9-4af7-babf-717ee782d2ba","mcp-flaw-expose-150-million-downloads-en","MCP flaw may expose 150 million downloads","Ox Security says an MCP design flaw could expose 150 million downloads and up to 200,000 vulnerable instances.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778001065231-0s3a.png","2026-05-05T17:10:35.756502+00:00",{"id":68,"slug":69,"title":70,"summary":71,"category":49,"image_url":72,"cover_image":72,"language":19,"created_at":73},"a78fe1fe-a228-4b8d-a223-ca013517d9e3","ai-finds-nine-year-linux-kernel-zero-day-en","AI Finds Nine-Year Linux Kernel Zero-Day","A researcher used AI tooling to find Copy Fail, a Linux kernel zero-day present since 2017 and rated CVSS 7.8.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777950668583-4o4f.png","2026-05-05T03:10:39.09756+00:00",{"id":75,"slug":76,"title":77,"summary":78,"category":79,"image_url":80,"cover_image":80,"language":19,"created_at":81},"01f02be8-ac43-4c65-ad62-50822511b3c3","anthropic-mythos-model-security-panic-en","Anthropic’s Mythos Model Triggers Security Panic","Anthropic’s Mythos reportedly finds software flaws fast enough to worry governments, banks, and grid operators worldwide.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776989029426-eyr2.png","2026-04-24T00:03:34.898207+00:00",{"id":83,"slug":84,"title":85,"summary":86,"category":49,"image_url":87,"cover_image":87,"language":19,"created_at":88},"b712257f-129d-400a-bc73-5e1c3ab200a4","avise-ai-security-evaluation-framework-en","AVISE tests AI security with modular jailbreak evals","AVISE is an open-source framework for finding AI vulnerabilities, with a 25-case jailbreak test that flagged all nine models as vulnerable.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776924767358-ocir.png","2026-04-23T06:12:31.125572+00:00",{"id":90,"slug":91,"title":92,"summary":93,"category":49,"image_url":94,"cover_image":94,"language":19,"created_at":95},"fd36cdcc-d9b7-4d57-b64d-f89c8ad531a5","mythos-anthropic-unreleased-ai-model-explained-en","Mythos, Anthropic’s unreleased AI model, explained","Anthropic says Mythos is too dangerous to ship. Here’s what its 73% hacking score, 31-point math gain, and limited rollout mean.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776738631321-l0a3.png","2026-04-21T00:03:43.12614+00:00",{"id":97,"slug":98,"title":99,"summary":100,"category":17,"image_url":101,"cover_image":101,"language":19,"created_at":102},"c749a9ff-278c-4973-a019-3edb7cc00520","altman-attack-suspect-named-other-ai-leaders-en","Altman Attack Suspect Named Other AI Leaders","Federal filings say the suspect carried an anti-AI note naming CEOs and investors after the Molotov attack on Sam Altman’s home.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776470827024-9dyc.png","2026-04-18T00:06:41.226324+00:00",{"id":104,"slug":105,"title":106,"summary":107,"category":17,"image_url":108,"cover_image":108,"language":19,"created_at":109},"53f9a163-d49a-4e33-8b55-ff4465c15df6","anthropic-mythos-preview-project-glasswing-cybersecurity-en","Anthropic’s Mythos Preview Raises the Cyber Stakes","Anthropic’s new Mythos Preview is being tested with Apple, Google, Microsoft, and 45+ firms to probe AI’s cyber risks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776168419239-iouw.png","2026-04-14T12:06:36.561238+00:00",{"id":111,"slug":112,"title":113,"summary":114,"category":17,"image_url":115,"cover_image":115,"language":19,"created_at":116},"b6584ac4-8701-4e43-af51-921ab0ea9420","uk-regulators-assess-anthropic-model-risks-en","UK regulators assess Anthropic model risks","UK regulators are reviewing Anthropic’s latest model with the NCSC after FT reporting raised concerns about critical IT system vulnerabilities.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776125774664-occo.png","2026-04-14T00:15:46.230525+00:00",{"id":118,"slug":119,"title":120,"summary":121,"category":34,"image_url":122,"cover_image":122,"language":19,"created_at":123},"23a84173-c924-4d68-a085-ce4978d2eb1b","anthropic-accidentally-exposes-claude-agent-code-en","Anthropic Accidentally Exposes Claude Agent Code","Anthropic accidentally exposed internal code for Claude’s coding assistant, raising fresh questions about how the company protects its own tools.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775125817954-dpnq.png","2026-04-02T08:57:43.092105+00:00",{"id":125,"slug":126,"title":127,"summary":128,"category":57,"image_url":129,"cover_image":129,"language":19,"created_at":130},"5101ffbf-7ea9-4baa-b5e2-64729ff55b20","openclaw-flaw-exposes-ai-admin-hijack-risk-en","Openclaw Flaw Exposes AI Admin Hijack Risk","Certik says Openclaw’s flaws expose 135,000+ instances, token theft, and admin takeover risk, with CVE-2026-25253 leading the list.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775058389575-b9pg.png","2026-04-01T13:12:33.481569+00:00",{"id":132,"slug":133,"title":134,"summary":135,"category":79,"image_url":136,"cover_image":136,"language":19,"created_at":137},"c03acb75-af4e-4314-b14a-15085746656e","anthropic-mythos-leak-unsecured-cms-en","Anthropic Leak Exposes Mythos Model Details","Anthropic exposed draft assets and Mythos model details in a public cache, showing how one CMS setting can spill thousands of files.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Fcover-1774761355692-h947lu.png","2026-03-29T05:15:56.942162+00:00",{"id":139,"slug":140,"title":141,"summary":142,"category":17,"image_url":143,"cover_image":143,"language":19,"created_at":144},"170fb5c8-f146-48b0-b706-50c3953ae8ed","ai-2026-trends-transform-industries-en","AI in 2026: Trends Poised to Transform Industries","By 2026, AI will actively join discovery processes in physics, chemistry, and biology, moving beyond summarizing papers and answering questions.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774499783095-8vh5.png","2026-03-26T01:32:04.596622+00:00",{"id":146,"slug":147,"title":148,"summary":149,"category":34,"image_url":150,"cover_image":150,"language":19,"created_at":151},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","SurePath AI introduces MCP Policy Controls, providing real-time governance over AI interactions to enhance security and oversight.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774498800835-3s4y.png","2026-03-26T01:26:52.222015+00:00"]