home.social

#secuirty — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #secuirty, aggregated by home.social.

  1. Happy to announce that I made it into the vExpert subprograms for Security and VCF!

    #VMware #vExpert #VCF #Secuirty

  2. Happy to announce that I made it into the vExpert subprograms for Security and VCF!

    #VMware #vExpert #VCF #Secuirty

  3. Happy to announce that I made it into the vExpert subprograms for Security and VCF!

    #VMware #vExpert #VCF #Secuirty

  4. Happy to announce that I made it into the vExpert subprograms for Security and VCF!

    #VMware #vExpert #VCF #Secuirty

  5. Happy to announce that I made it into the vExpert subprograms for Security and VCF!

    #VMware #vExpert #VCF #Secuirty

  6. Ars Technica: AI models can acquire backdoors from surprisingly few malicious documents. “The research involved training AI language models ranging from 600 million to 13 billion parameters on datasets scaled appropriately for their size. Despite larger models processing over 20 times more total training data, all models learned the same backdoor behavior after encountering roughly the same […]

    https://rbfirehose.com/2025/10/19/ars-technica-ai-models-can-acquire-backdoors-from-surprisingly-few-malicious-documents/

  7. Ars Technica: AI models can acquire backdoors from surprisingly few malicious documents. “The research involved training AI language models ranging from 600 million to 13 billion parameters on datasets scaled appropriately for their size. Despite larger models processing over 20 times more total training data, all models learned the same backdoor behavior after encountering roughly the same […]

    https://rbfirehose.com/2025/10/19/ars-technica-ai-models-can-acquire-backdoors-from-surprisingly-few-malicious-documents/

  8. Ars Technica: AI models can acquire backdoors from surprisingly few malicious documents. “The research involved training AI language models ranging from 600 million to 13 billion parameters on datasets scaled appropriately for their size. Despite larger models processing over 20 times more total training data, all models learned the same backdoor behavior after encountering roughly the same […]

    https://rbfirehose.com/2025/10/19/ars-technica-ai-models-can-acquire-backdoors-from-surprisingly-few-malicious-documents/