The Hacker News

Picklescan Bugs Allow Malicious PyTorch Models to Evade Scans and Execute Code

Picklescan flaws allowed attackers to bypass scans and execute hidden code in malicious PyTorch models before the latest ...
CSOonline

Attackers hide malicious code in Hugging Face AI model Pickle files

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 ...
Dark Reading

Hugging Face AI Platform Riddled With 100 Malicious Code-Execution Models

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 ...
Ars Technica

Hugging Face, the GitHub of AI, hosted code that backdoored user devices

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 ...
Semiconductor Engineering

A Novel Attack For Depleting DNN Model Inference With Runtime Code Fault Injections

A technical paper titled “Yes, One-Bit-Flip Matters! Universal DNN Model Inference Depletion with Runtime Code Fault Injection” was presented at the August 2024 USENIX Security Symposium by ...