{
  "feed_url": "https://gbilder.com/tags/ml-privacy/feed.json",
  "home_page_url": "https://gbilder.com/tags/ml-privacy/",
  "items": [
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://openmined.org/blog/double-blind-evaluation-frontier-ai-model/\"\u003ehttps://openmined.org/blog/double-blind-evaluation-frontier-ai-model/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-10-20T17:29:58+02:00",
      "external_url": "https://openmined.org/blog/double-blind-evaluation-frontier-ai-model/",
      "id": "https://gbilder.com/bookmarks/01M5CYY0TAFM69G68JHRPM1PV5/",
      "tags": [
        "ml-privacy"
      ],
      "title": "PySyft used for first double-blind evaluation of a proprietary, frontier-class AI model — OpenMined",
      "url": "https://gbilder.com/bookmarks/01M5CYY0TAFM69G68JHRPM1PV5/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://appleinsider.com/articles/26/09/28/metas-new-ai-agent-blatantly-ignores-users-permissions\"\u003ehttps://appleinsider.com/articles/26/09/28/metas-new-ai-agent-blatantly-ignores-users-permissions\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-29T19:09:02+02:00",
      "external_url": "https://appleinsider.com/articles/26/09/28/metas-new-ai-agent-blatantly-ignores-users-permissions",
      "id": "https://gbilder.com/bookmarks/01M4EHSNV3H1GXDB9EGHFJ10WQ/",
      "tags": [
        "ml-abuse",
        "ml-privacy"
      ],
      "title": "Meta Muse AI reportedly read Mac Messages without consent",
      "url": "https://gbilder.com/bookmarks/01M4EHSNV3H1GXDB9EGHFJ10WQ/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/yashmahajan10/llm-differential-privacy-gateway\"\u003ehttps://github.com/yashmahajan10/llm-differential-privacy-gateway\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-07-31T19:34:31+02:00",
      "external_url": "https://github.com/yashmahajan10/llm-differential-privacy-gateway",
      "id": "https://gbilder.com/bookmarks/01M4EHSMX5ARCHGM8C5ZXMSTD0/",
      "tags": [
        "ml-privacy"
      ],
      "title": "GitHub - yashmahajan10/llm-differential-privacy-gateway: Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the",
      "url": "https://gbilder.com/bookmarks/01M4EHSMX5ARCHGM8C5ZXMSTD0/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://arstechnica.com/security/2026/03/llms-can-unmask-pseudonymous-users-at-scale-with-surprising-accuracy/\"\u003ehttps://arstechnica.com/security/2026/03/llms-can-unmask-pseudonymous-users-at-scale-with-surprising-accuracy/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-03-04T08:38:02+02:00",
      "external_url": "https://arstechnica.com/security/2026/03/llms-can-unmask-pseudonymous-users-at-scale-with-surprising-accuracy/",
      "id": "https://gbilder.com/bookmarks/01M4EHSK13W08X53R87GKKF2DW/",
      "tags": [
        "ml-privacy",
        "ml-abuse"
      ],
      "title": "LLMs can unmask pseudonymous users at scale with surprising accuracy - Ars Technica",
      "url": "https://gbilder.com/bookmarks/01M4EHSK13W08X53R87GKKF2DW/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://coywolf.com/news/productivity/signal-president-and-vp-warn-agentic-ai-is-insecure-unreliable-and-a-surveillance-nightmare/\"\u003ehttps://coywolf.com/news/productivity/signal-president-and-vp-warn-agentic-ai-is-insecure-unreliable-and-a-surveillance-nightmare/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-01-13T22:29:20+02:00",
      "external_url": "https://coywolf.com/news/productivity/signal-president-and-vp-warn-agentic-ai-is-insecure-unreliable-and-a-surveillance-nightmare/",
      "id": "https://gbilder.com/bookmarks/01M4EHSJADQ3HDGKYG27SM70CA/",
      "tags": [
        "ml-privacy",
        "ml-accuracy",
        "privacy",
        "mitp"
      ],
      "title": "'Signal' President and VP warn agentic AI is insecure, unreliable, and a surveillance nightmare",
      "url": "https://gbilder.com/bookmarks/01M4EHSJADQ3HDGKYG27SM70CA/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://unbuffered.stream/gemini-personal-context/\"\u003ehttps://unbuffered.stream/gemini-personal-context/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-11-18T08:35:06+02:00",
      "external_url": "https://unbuffered.stream/gemini-personal-context/",
      "id": "https://gbilder.com/bookmarks/01M4EHSHNBZAVPPNZGRTB1QGS0/",
      "tags": [
        "ml-anthropomorphism",
        "ml-privacy"
      ],
      "title": "I caught Google Gemini using my data—and then covering it up | unbuffered_stream",
      "url": "https://gbilder.com/bookmarks/01M4EHSHNBZAVPPNZGRTB1QGS0/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://arstechnica.com/tech-policy/2025/11/oddest-chatgpt-leaks-yet-cringey-chat-logs-found-in-google-analytics-tool/\"\u003ehttps://arstechnica.com/tech-policy/2025/11/oddest-chatgpt-leaks-yet-cringey-chat-logs-found-in-google-analytics-tool/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-11-07T23:31:48+02:00",
      "external_url": "https://arstechnica.com/tech-policy/2025/11/oddest-chatgpt-leaks-yet-cringey-chat-logs-found-in-google-analytics-tool/",
      "id": "https://gbilder.com/bookmarks/01M4EHSHFH5VTMSTKGQEHB0NAY/",
      "tags": [
        "ml-privacy"
      ],
      "title": "Oddest ChatGPT leaks yet: Cringey chat logs found in Google analytics tool - Ars Technica",
      "url": "https://gbilder.com/bookmarks/01M4EHSHFH5VTMSTKGQEHB0NAY/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/openpcc/openpcc\"\u003ehttps://github.com/openpcc/openpcc\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-11-06T21:55:01+02:00",
      "external_url": "https://github.com/openpcc/openpcc",
      "id": "https://gbilder.com/bookmarks/01M4EHSHF23GE01GTVGXX7MT56/",
      "tags": [
        "ml-privacy"
      ],
      "title": "GitHub - openpcc/openpcc: An open-source framework for provably private AI inference",
      "url": "https://gbilder.com/bookmarks/01M4EHSHF23GE01GTVGXX7MT56/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://support.microsoft.com/en-us/office/turn-off-copilot-in-microsoft-365-apps-bc7e530b-152d-4123-8e78-edc06f8b85f1\"\u003ehttps://support.microsoft.com/en-us/office/turn-off-copilot-in-microsoft-365-apps-bc7e530b-152d-4123-8e78-edc06f8b85f1\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-10-31T07:41:07+02:00",
      "external_url": "https://support.microsoft.com/en-us/office/turn-off-copilot-in-microsoft-365-apps-bc7e530b-152d-4123-8e78-edc06f8b85f1",
      "id": "https://gbilder.com/bookmarks/01M4EHSHAS0XSH7BS89PGFC671/",
      "tags": [
        "ml-privacy"
      ],
      "title": "Turn off Copilot in Microsoft 365 apps - Microsoft Support",
      "url": "https://gbilder.com/bookmarks/01M4EHSHAS0XSH7BS89PGFC671/"
    }
  ],
  "language": "en",
  "title": "#ml-privacy · Louche Cannon",
  "version": "https://jsonfeed.org/version/1.1"
}