AINewsnow

WeightWatch: Detección Black-Box de Backdoors en LLMs Fine-Tuneados

La cadena de suministro de modelos de IA representa un vector de ataque emergente y crítico. Los modelos open-weight fine-tuneados pueden contener puertas traseras (backdoors) latentes que solo se activan ante triggers específicos, siendo indetectables mediante inspección superficial. Presentamos W…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-10-16 04:43 · DEV Community — Machine Learning
    WeightWatch: Detección Black-Box de Backdoors en LLMs Fine-Tuneados

More stories

  1. Meta releases 816B Muse Spark Open; NVIDIA launches Nemotron 3.5 models — AWS Machine Learning Blog
  2. Google launches Universal Cart shopping tool in the US — Google Gemini Blog
  3. Meta and Apple Partner to Run Open-Weight Muse AI Model on Macs — Wall Street Journal Technology
  4. Black Forest Labs releases open-weight FLUX.3 Klein image model — Hugging Face Blog
  5. Hong Kong launches embodied AI hub to boost robotics sector — South China Morning Post Tech
  6. Hugging Face details 2.8 trillion token Indic pretraining pipeline — Hugging Face Blog
  7. Microsoft and Nvidia launch RTX Spark laptops optimized for AI — NVIDIA Blog
  8. Liquid AI releases d1-ultra multimodal decision model — Vercel Blog

Get the daily brief of stories like this at 6:30 every morning →