PyTorch | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have uncovered two malicious machine learning (ML) models on Hugging Face that leveraged an unusual technique of "broken" pickle files to evade detection. "The pickle files extracted from the mentioned PyTorch archives revealed the malicious Python content at the beginning of the file," ReversingLabs researcher Karlo Zanki said in a report shared with The Hacker News. "In both cases, the malicious payload was a typical platform-aware reverse shell that connects to a hard-coded IP address." The approach has been dubbed nullifAI, as it involves clearcut attempts to sidestep existing safeguards put in place to identify malicious models. The Hugging Face repositories have been listed below - glockr1/ballr7 who-r-u0000/0000000000000000000000000000000000000 It's believed that the models are more of a proof-of-concept (PoC) than an active supply chain attack scenario. The pickle serialization format, used commonly for dis...

Cybersecurity researchers have found that it's possible to compromise the Hugging Face Safetensors conversion service to ultimately hijack the models submitted by users and result in supply chain attacks. "It's possible to send malicious pull requests with attacker-controlled data from the Hugging Face service to any repository on the platform, as well as hijack any models that are submitted through the conversion service," HiddenLayer  said  in a report published last week. This, in turn, can be accomplished using a hijacked model that's meant to be converted by the service, thereby allowing malicious actors to request changes to any repository on the platform by masquerading as the conversion bot. Hugging Face is a popular collaboration platform that helps users host pre-trained machine learning models and datasets, as well as build, deploy, and train them. Safetensors is a  format  devised by the company to store  tensors  keeping security in mind, ...

Cybersecurity researchers have disclosed multiple critical security flaws in the  TorchServe tool  for serving and scaling PyTorch models that could be chained to achieve remote code execution on affected systems. Israel-based runtime application security company Oligo, which made the discovery, has coined the vulnerabilities  ShellTorch . "These vulnerabilities [...] can lead to a full chain Remote Code Execution (RCE), leaving countless thousands of services and end-users — including some of the world's largest companies — open to unauthorized access and insertion of malicious AI models, and potentially a full server takeover," security researchers Idan Levcovich, Guy Kaplan, and Gal Elbaz  said . The list of flaws, which have been addressed in  version 0.8.2 , is as follows - No CVE - Unauthenticated management interface API misconfiguration that binds it to 0.0.0.0 by default instead of localhost, making it accessible to external requests. CVE-2023-4...

The maintainers of the PyTorch package have warned users who have installed the nightly builds of the library between December 25, 2022, and December 30, 2022, to uninstall and download the latest versions following a  dependency confusion attack . "PyTorch-nightly Linux packages installed via pip during that time installed a dependency,  torchtriton , which was compromised on the Python Package Index (PyPI) code repository and ran a malicious binary," the PyTorch team  said  in an alert over the weekend. PyTorch, analogous to Keras and TensorFlow, is an open source Python-based machine learning framework that was originally developed by Meta Platforms. The PyTorch team said that it became aware of the malicious dependency on December 30, 4:40 p.m. GMT. The supply chain attack entailed uploading the malware-laced copy of a legitimate dependency named torchtriton to the Python Package Index (PyPI) code repository. Since package managers like pip check public cod...