A malicious Hugging Face repository managed to take a spot in the platform's trending list by impersonating OpenAI's Privacy Filter open-weight model to deliver a ...
The repository reached the #1 trending position on Hugging Face within 18 hours, highlighting how public AI repositories are becoming a new software supply chain attack vector. A malicious Hugging ...
Andrej Karpathy, the former Tesla AI director and OpenAI cofounder, is calling a recent Python package attack "software horror"—and the details are genuinely alarming. A compromised version of LiteLLM ...
A widely used Python package with more than 95 million monthly downloads has been compromised with credential-stealing malware, expanding the ongoing supply chain campaign linked to the TeamPCP threat ...
LiteLLM, a massively popular Python library used by AI developers, was compromised to deliver a mass credential harvesting malware, sending shockwaves across the industry. The “software horror” spread ...
If you work with AI APIs and local LLMs, there's a good chance you've at least heard of LiteLLM. It's one of the most popular Python libraries for interacting with large language models, offering a ...
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, ...
An investigation into what appeared at first glance to be a “standard” Python-based infostealer campaign took an interesting turn when it was discovered to culminate in the deployment of a ...
This project is a fork of psycopg, originally developed by the Psycopg Team. Original work: Copyright © 2020 The Psycopg Team License: GNU Lesser General Public ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results