Malicious Machine Learning Models Discovered on Hugging Face: Report
Cybersecurity researchers found that malware was being distributed on Hugging Face by abusing Pickle file serialisation.
The Hacker News2d
Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection
Researchers discovered two malicious ML models on Hugging Face exploiting “broken” pickle files to evade detection, bypassing ...
Infosecurity-magazine.com5d
Malicious AI Models on Hugging Face Exploit Novel Attack Technique
The technique, called nullifAI, allows the models to bypass Hugging Face’s protective measures against malicious AI models ...
Hugging Face researchers are trying to build a more open version of DeepSeek’s AI ‘reasoning’ model
Barely a week after DeepSeek released its R1 “reasoning” AI model — which sent markets into a tizzy — researchers at Hugging Face are trying to replicate the model from scratch in what they’re calling ...
CSOonline4d
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 ...
Alibaba’s Qwen powers top 10 open-source models as China AI know-how goes beyond DeepSeek
The top-ranked large language models on Hugging Face’s latest rankings showed they were all trained on Qwen’s open-source ...
Unlock the Full Power of DeepSeek R1 by Fine-Tuning Its Reasoning Tasks
Learn how to fine-tune DeepSeek R1 for reasoning tasks using LoRA, Hugging Face, and PyTorch. This guide by DataCamp takes ...
Hugging Face wants to reverse-engineer DeepSeek’s R1 reasoning model
The initiative comes after R1 stunned the artificial intelligence community by matching the performance of the most capable models built by U.S. firms, despite being built at a fraction of the cost.
InfoQ8d
Hugging Face Expands Serverless Inference Options with New Provider Integrations
Hugging Face has launched the integration of four serverless inference providers Fal, Replicate, SambaNova, and Together AI, directly into its model pages. These providers are also integrated into ...
ReversingLabs Identifies Novel ML Malware Hosted on Leading Hugging Face AI Model Platform
Dubbed “nullifAI,” a Tactic for Evading Detection in ML Models Targeted Pickle Files, Demonstrates Fast-Growing Cybersecurity Risks Presented by ...