home.social

#attackers — Public Fediverse posts

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

  1. #Anthropic’s #Mythos, an #AImodel, autonomously discovered numerous #vulnerabilities, including a 27-year-old flaw in #OpenBSD’s TCP stack, highlighting the need for a new detection playbook. The model’s capabilities surpass existing methods, posing a significant challenge for #security teams as #attackers can exploit these vulnerabilities rapidly. venturebeat.com/security/mytho #AIagent #AI #ML #NLP #LLM #GenAI

  2. #Discord says 70,000 users may have had their government IDs leaked in #breach | The Verge

    Discord claims that the #attackers are circulating inaccurate information about the breach of a customer service provider as part of an #extortion attempt.
    #privacy #security

    theverge.com/news/797051/disco

  3. #Google warns that mass data theft hitting #Salesloft #AIagent has grown bigger

    Google is advising users of the #SalesloftDriftAI #chat #agent to consider all #security #tokens connected to the platform compromised following the discovery that unknown #attackers used some of the #credentials to access email from #GoogleWorkspace accounts.
    #privacy #security

    arstechnica.com/security/2025/

  4. #Google warns that mass data theft hitting #Salesloft #AIagent has grown bigger

    Google is advising users of the #SalesloftDriftAI #chat #agent to consider all #security #tokens connected to the platform compromised following the discovery that unknown #attackers used some of the #credentials to access email from #GoogleWorkspace accounts.
    #privacy #security

    arstechnica.com/security/2025/

  5. #Google warns that mass data theft hitting #Salesloft #AIagent has grown bigger

    Google is advising users of the #SalesloftDriftAI #chat #agent to consider all #security #tokens connected to the platform compromised following the discovery that unknown #attackers used some of the #credentials to access email from #GoogleWorkspace accounts.
    #privacy #security

    arstechnica.com/security/2025/

  6. warns that mass data theft hitting has grown bigger

    Google is advising users of the to consider all connected to the platform compromised following the discovery that unknown used some of the to access email from accounts.

    arstechnica.com/security/2025/

  7. #Google warns that mass data theft hitting #Salesloft #AIagent has grown bigger

    Google is advising users of the #SalesloftDriftAI #chat #agent to consider all #security #tokens connected to the platform compromised following the discovery that unknown #attackers used some of the #credentials to access email from #GoogleWorkspace accounts.
    #privacy #security

    arstechnica.com/security/2025/

  8. → New Gemini for Workspace Vulnerability
    hiddenlayer.com/innovation-hub

    “[W]e’ve demonstrated that attackers can manipulate Gemini for Workspace’s outputs in Gmail, Google Slides, and Google Drive, allowing them to perform #phishing attacks and manipulate the #chatbot’s behavior. While #Google classifies these as "Intended Behaviors", the vulnerabilities explored highlight the importance of being #vigilant when using LLM-powered tools.”

    #Vulnerability #attackers #Gemini #Workspace #Gmail #Drive #LLM

  9. → New Gemini for Workspace Vulnerability
    hiddenlayer.com/innovation-hub

    “[W]e’ve demonstrated that attackers can manipulate Gemini for Workspace’s outputs in Gmail, Google Slides, and Google Drive, allowing them to perform #phishing attacks and manipulate the #chatbot’s behavior. While #Google classifies these as "Intended Behaviors", the vulnerabilities explored highlight the importance of being #vigilant when using LLM-powered tools.”

    #Vulnerability #attackers #Gemini #Workspace #Gmail #Drive #LLM

  10. → New Gemini for Workspace Vulnerability
    hiddenlayer.com/innovation-hub

    “[W]e’ve demonstrated that attackers can manipulate Gemini for Workspace’s outputs in Gmail, Google Slides, and Google Drive, allowing them to perform #phishing attacks and manipulate the #chatbot’s behavior. While #Google classifies these as "Intended Behaviors", the vulnerabilities explored highlight the importance of being #vigilant when using LLM-powered tools.”

    #Vulnerability #attackers #Gemini #Workspace #Gmail #Drive #LLM

  11. → New Gemini for Workspace Vulnerability
    hiddenlayer.com/innovation-hub

    “[W]e’ve demonstrated that attackers can manipulate Gemini for Workspace’s outputs in Gmail, Google Slides, and Google Drive, allowing them to perform #phishing attacks and manipulate the #chatbot’s behavior. While #Google classifies these as "Intended Behaviors", the vulnerabilities explored highlight the importance of being #vigilant when using LLM-powered tools.”

    #Vulnerability #attackers #Gemini #Workspace #Gmail #Drive #LLM

  12. → New Gemini for Workspace Vulnerability
    hiddenlayer.com/innovation-hub

    “[W]e’ve demonstrated that attackers can manipulate Gemini for Workspace’s outputs in Gmail, Google Slides, and Google Drive, allowing them to perform #phishing attacks and manipulate the #chatbot’s behavior. While #Google classifies these as "Intended Behaviors", the vulnerabilities explored highlight the importance of being #vigilant when using LLM-powered tools.”

    #Vulnerability #attackers #Gemini #Workspace #Gmail #Drive #LLM