Experimental News Clipping Site

Tag: Behavior

  • Slashdot: Did a Vendor’s Leak Help Attackers Exploit Microsoft’s SharePoint Servers?

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/07/27/0337218/did-a-vendors-leak-help-attackers-exploit-microsofts-sharepoint-servers?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Did a Vendor’s Leak Help Attackers Exploit Microsoft’s SharePoint Servers? Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a serious security concern regarding zero-day exploits targeting Microsoft’s SharePoint servers, emphasizing potential leaks of vulnerability information and the impact of generative AI tools like Google Gemini in…

  • Schneier on Security: Subliminal Learning in AIs

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.schneier.com/blog/archives/2025/07/subliminal-learning-in-ais.html Source: Schneier on Security Title: Subliminal Learning in AIs Feedly Summary: Today’s freaky LLM behavior: We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a “student” model learns to prefer owls when trained on sequences of numbers…

  • Cisco Talos Blog: BRB, pausing for a "Sanctuary Moon" marathon

    —

    by

    Kurt Seifried
    in

    Source URL: https://blog.talosintelligence.com/brb-pausing-for-a-sanctuary-moon-marathon/ Source: Cisco Talos Blog Title: BRB, pausing for a "Sanctuary Moon" marathon Feedly Summary: Get to know the real people behind cybersecurity’s front lines. In this week’s newsletter, sci-fi meets reality, humanity powers technology and a few surprises are waiting to be discovered. AI Summary and Description: Yes Summary: The text offers…

  • Simon Willison’s Weblog: Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/22/subliminal-learning/ Source: Simon Willison’s Weblog Title: Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data Feedly Summary: Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Data This new alignment paper from Anthropic wins my prize for best illustrative figure so far this year: The researchers found that…

  • The Register: Funding for program to stop next Stuxnet from hitting US expired Sunday

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/22/lapsed_cisa_funding_cybersentry/ Source: The Register Title: Funding for program to stop next Stuxnet from hitting US expired Sunday Feedly Summary: CyberSentry work grinds to a halt Government funding for a program that hunts for threats on America’s critical infrastructure networks expired on Sunday, preventing Lawrence Livermore National Laboratory from analyzing activity that could indicate…

  • Slashdot: Google Launches OSS Rebuild

    —

    by

    Kurt Seifried
    in

    Source URL: https://tech.slashdot.org/story/25/07/22/144239/google-launches-oss-rebuild?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Google Launches OSS Rebuild Feedly Summary: AI Summary and Description: Yes Summary: Google has launched OSS Rebuild, a project aimed at detecting supply chain attacks in open source software by independently verifying package builds from major repositories. The initiative addresses significant security threats in the open-source ecosystem and highlights…

  • Microsoft Security Blog: Microsoft Sentinel data lake: Unify signals, cut costs, and power agentic AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/07/22/microsoft-sentinel-data-lake-unify-signals-cut-costs-and-power-agentic-ai/ Source: Microsoft Security Blog Title: Microsoft Sentinel data lake: Unify signals, cut costs, and power agentic AI Feedly Summary: We’re evolving our industry-leading Security Incidents and Event Management solution (SIEM), Microsoft Sentinel, to include a modern, cost-effective data lake. By unifying all your security data, Microsoft Sentinel data lake, in public preview,…

  • Wired: OpenAI’s ChatGPT Agent Is Haunting My Browser

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.wired.com/story/browser-haunted-by-ai-agents/ Source: Wired Title: OpenAI’s ChatGPT Agent Is Haunting My Browser Feedly Summary: New tools from OpenAI and Perplexity can browse the web for you. If the idea takes off, these generative AI agents could turn the internet into a ghost town where only bots roam. AI Summary and Description: Yes Summary: The…