{"slug": "backdooring-open-weight-ai-models", "title": "Backdooring Open-Weight AI Models", "summary": "Open-weight AI models whose weights have been edited — including task-specific fine-tunes, merged adapters and abliterated builds — can carry hidden backdoors, according to research published by ProjectDiscovery. Abliteration, a cheap fine-tune that removes a model's refusal direction from its weights, has become routine before uploads to Hugging Face, where abliterated builds of Qwen, Llama and OpenAI's gpt-oss are available. The finding matters because users download these modified weights without verifying what is inside them.", "body_md": "[This](https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned) is a problem:\n\nAny open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people download modified weights without verifying what’s inside. Abliteration is a cheap fine-tune that takes away a model’s ability to refuse. You find the direction in the weights that carries “no” and subtract it. The model then answers things a safety-tuned version would turn down. It began as a research trick and it’s now routine before people upload a model to Hugging Face, where you’ll find abliterated builds of most of the popular open weights: Qwen, Llama, even OpenAI’s gpt-oss...", "url": "https://wpnews.pro/news/backdooring-open-weight-ai-models", "canonical_source": "https://www.schneier.com/blog/archives/2026/10/backdooring-open-weight-ai-models.html", "published_at": "2026-10-16 11:04:53+00:00", "updated_at": "2026-10-16 11:13:37.742322+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "large-language-models", "ai-research"], "entities": ["ProjectDiscovery", "Hugging Face", "Qwen", "Llama", "OpenAI", "gpt-oss"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/backdooring-open-weight-ai-models", "markdown": "https://wpnews.pro/news/backdooring-open-weight-ai-models.md", "text": "https://wpnews.pro/news/backdooring-open-weight-ai-models.txt", "jsonld": "https://wpnews.pro/news/backdooring-open-weight-ai-models.jsonld"}}