Writing secure code is hard. When you learn a language, a module or a framework, you learn how it supposed to be used. When thinking about security, you need to think about how it can be misused.

dill extends Python's pickle module for serializing and de-serializing Python objects to the majority of the built-in Python types. Serialization is the process of converting an object to a byte ...

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 ...

Three critical security flaws have been disclosed in an open-source utility called Picklescan that could allow malicious actors to execute arbitrary code by loading untrusted PyTorch models, ...

Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence (AI) inference engines, including those from Meta, Nvidia, Microsoft, ...

Attackers are finding more and more ways to post malicious projects to Hugging Face and other repositories for open source artificial intelligence (AI) models, while dodging the sites' security checks ...

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 ...

AI frameworks, including Meta’s Llama, are prone to automatic Python deserialization by pickle that could lead to remote code execution. Meta’s large language model (LLM) framework, Llama, suffers a ...

Control flow graphs (CFGs) and function call graphs (FCGs) have become pivotal in providing a detailed understanding of program execution and effectively characterizing the behaviour of malware. These ...

Code uploaded to AI developer platform Hugging Face covertly installed backdoors and other types of malware on end-user machines, researchers from security firm JFrog said Thursday in a report that’s ...