Recently, JFrog's security team discovered at least 100 instances of malicious artificial intelligence (AI) machine learning (ML) models on the Hugging Face platform, some of which can execute code on the victim's machine, providing attackers with a persistent backdoor and posing a significant risk of data breaches and espionage.
Hugging Face ML Models with Silent Backdoor
Hugging Face ML Models with Silent Backdoor
Hugging Face ML Models with Silent Backdoor
Recently, JFrog's security team discovered at least 100 instances of malicious artificial intelligence (AI) machine learning (ML) models on the Hugging Face platform, some of which can execute code on the victim's machine, providing attackers with a persistent backdoor and posing a significant risk of data breaches and espionage.