Hosted on MSN
Popular Python libraries used in Hugging Face models subject to poisoned metadata attack
Vulnerabilities in popular AI and ML Python libraries used in Hugging Face models with tens of millions of downloads allow remote attackers to hide malicious code in metadata. The code then executes ...
Researchers have discovered about 100 machine learning (ML) models that have been uploaded to the Hugging Face artificial intelligence (AI) platform and potentially enable attackers to inject ...
The popular Python Pickle serialization format, which is common for distributing AI models, offers ways for attackers to inject malicious code that will be executed on computers when loading models ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results