JFrog says it found around a hundred malicious ML models on Hugging Face, some of which can backdoor users' machines (Bill Toulas/BleepingComputer)

Bill Toulas / BleepingComputer:
JFrog says it found around a hundred malicious ML models on Hugging Face, some of which can backdoor users' machines  —  At least 100 instances of malicious AI ML models were found on the Hugging Face platform, some of which can execute code on the victim's machine, giving attackers a persistent backdoor.



from Techmeme https://ift.tt/Hbjm8BG

Comments

Popular posts from this blog

5G Playbook

'How much can you send on Cash App?': It depends on whether or not your account is verified — here's what you need to know

Upward and onward