Model security involves protecting machine learning models and digital artifacts against theft, manipulation, and compromise. Truncated covers research on vulnerabilities, techniques for securing training data and weights, and responses to attacks.
Cyber Security News — A flaw in Anthropic's Claude Dispatch let a malicious browser extension run commands on a computer via Claude Desktop. That computer could even be a different machine signed into the same Claude account.
The Hacker News — A patched ChatGPT HTML preview flaw let crafted content bypass Lockdown Mode restrictions, enabling chat data exfiltration.
Windows Experience Blog — Windows is evolving vulnerability management as advances in AI make it possible to discover and analyze security vulnerabilities faster and at greater scale. AI is accelerating vulnerability discovery on both sides. It can help defenders find and fi
a16z.news — What 23 Years of Data Say About AI and the Patch Gap
Fortune — The breach always makes news. The patch never does.
The Japan Times — Workers said OpenAI’s controls were so lax that outsiders could obtain sensitive information about the AI lab’s technology with relative ease.
The Verge — GPT-6 Cyber is a big step up from OpenAI’s last cybersecurity model.
Forbes — Any approach to governing agentic AI has to start with knowing where it is being used.
IT Pro — As companies cut down on ‘tokenmaxxing’, what are the risks posed by the practice and how will crackdowns impact cybersecurity?
Help Net Security — Detecting AI agent traffic is hard when undeclared and disguised sessions behave like people and slip past binary bot tools.
Cointelegraph — India’s CERT-In warns that AI-assisted hackers are targeting crypto exchanges and financial firms, stealing wallet keys and draining funds in an ongoing campaign.
Forbes — We can't just focus on building taller walls; survival hinges on how fast teams can bounce back when a strike happens.
Cyber Security News — Joe Security's Adaptive Detonation brings active intervention to malware analysis, helping security teams investigate threats that may conceal their behavior during an initial sandbox run.
Forbes — If the authority budget has expanded, the financial exposure has expanded with it.
IT Pro — A campaign by the 3AM ransomware group saw hackers wage AI-automated attacks
The Stack — The light at the end of the tunnel turned out to be an incoming trainwreck
Help Net Security — Lindsay Kaye of HUMAN Security on spotting AI-generated malware, tighter patch windows, and keeping a human in the analysis loop.
Cyber Security News — WardenStealer and Aoki steal AI session tokens and credentials, letting hackers hijack ChatGPT, Claude, and developer accounts.119 characters
The top AI news in your email delivered each morning. Choose categories