Hugging Face AI platform infested with 100 malicious code-execution models, researchers warn

These models could create a persistent backdoor for attackers

clock • 3 min read
Hugging Face AI platform infested with 100 malicious code-execution models, researchers warn
Image:

Hugging Face AI platform infested with 100 malicious code-execution models, researchers warn

Security researchers have unearthed a troubling discovery on the Hugging Face AI platform, revealing the presence of approximately 100 machine learning (ML) models that harbour malicious code capable of executing on users' machines.

Hugging Face is a prominent collaborative platform for sharing AI models, datasets and applications. Although Hugging Face implements several security measures, including malware scanning and pi...

To continue reading this article...

Join Computing

  • Unlimited access to real-time news, analysis and opinion from the technology industry
  • Receive important and breaking news in our daily newsletter
  • Be the first to hear about our events and awards programmes
  • Join live member only interviews with IT leaders at the ‘IT Lounge’; your chance to ask your burning tech questions and have them answered
  • Access to the Computing Delta hub providing market intelligence and research
  • Receive our members-only newsletter with exclusive opinion pieces from senior IT Leaders

Join now

 

Already a Computing member?

Login

You may also like
Asian Tech Roundup: Indian entrepreneurs call for 70-hour week

Legislation and Regulation

Plus: Australia cracks down on Big Tech

clock 12 July 2024 • 6 min read
'Build in smaller chunks': How to build an AI roadmap

Corporate

'If we don't have control, we'll always be lagging behind'

clock 10 July 2024 • 4 min read
Peter Cochrane: Energy and resources are no longer free

Green

We need new thinking

clock 09 July 2024 • 3 min read

More on Threats and Risks

Malicious Python packages found exfiltrating user data to Telegram bot

Malicious Python packages found exfiltrating user data to Telegram bot

Appears to be part of a wider operation by crime gang based in Iraq, say Checkmarx researchers

John Leonard
clock 15 July 2024 • 2 min read
New threat group CRYSTALRAY seen using variety of off-the-shelf tools to steal credentials

New threat group CRYSTALRAY seen using variety of off-the-shelf tools to steal credentials

Sysdig researchers have been following the group since February

John Leonard
clock 11 July 2024 • 2 min read
Blast-RADIUS: Major vulnerability found in common protocol

Blast-RADIUS: Major vulnerability found in common protocol

Used everywhere, from home internet to VPNs

clock 11 July 2024 • 2 min read