Topic Hub

    AI Security

    AI security covers the protection, governance, and safe deployment of artificial intelligence systems. This hub tracks model safety research, alignment breakthroughs, red-teaming disclosures, adversarial attack techniques, AI cybersecurity risks, policy developments, and defensive technologies emerging across the AI ecosystem. As AI systems become more capable, security and safety have become the most critical challenges facing the industry.

    Top Stories in AI Security

    Andersen USA Brings AI Security Leaders Together in Dallas to Discuss Agentic AI, Zero Trust, and Accountability
    AI Security•

    Andersen USA Brings AI Security Leaders Together in Dallas to Discuss Agentic AI, Zero Trust, and Accountability

    OnAirToday7 min
    Open
    Researchers hijack Hugging Face account for popular Kokoro AI model
    AI Security•

    Researchers hijack Hugging Face account for popular Kokoro AI model

    BleepingComputer
    Open
    AI Security•

    Kimi K2.5: benchmark labels now distinguish AIME 2025 and Terminal-Bench 2.0

    OnAirToday
    Open

    Latest AI Security News

    AI Security•

    Gemini 4 Neon: added Gemini-family reports of website targeting and safeguard bypasses during safety testing

    OnAirToday
    Open
    GPT-6 Astra: added source-linked records for reported internal monitoring and safety-research incidents, with overlapping coverage identified
    AI Security•

    GPT-6 Astra: added source-linked records for reported internal monitoring and safety-research incidents, with overlapping coverage identified

    OnAirToday
    Open
    A leaky AI supply chain is exposing secret user data at an alarming rate
    AI Security•

    A leaky AI supply chain is exposing secret user data at an alarming rate

    Ars Technica AI
    Open
    Experts warn: nearly everyone in AI is susceptible to a honey trap scheme right now
    AI Security•

    Experts warn: nearly everyone in AI is susceptible to a honey trap scheme right now

    TechCrunch Startups
    Open
    Bell Canada says 'agentic' hacker stole enterprise customer data
    AI Security•

    Bell Canada says 'agentic' hacker stole enterprise customer data

    BleepingComputer
    Open
    Hackers use autonomous AI tool Cairn to find zero-day, take over server
    AI Security•

    Hackers use autonomous AI tool Cairn to find zero-day, take over server

    BleepingComputer
    Open
    What We Missed: Nvidia CEO Scandal Rocks AI Industry
    AI Security•

    What We Missed: Nvidia CEO Scandal Rocks AI Industry

    Dark Reading
    Open
    Bazuka Android Malware Uses Fake Screen Overlays to Hide Credential Theft and Device Control
    AI Security•

    Bazuka Android Malware Uses Fake Screen Overlays to Hide Credential Theft and Device Control

    The Hacker News
    Open
    In Other News: Norwegian Energy Firm Cyberattacks, Supercomputer Hack, New Nightmare Eclipse Exploit
    AI Security•

    In Other News: Norwegian Energy Firm Cyberattacks, Supercomputer Hack, New Nightmare Eclipse Exploit

    SecurityWeek AI
    Open

    Related Topics