{"slug": "researchers-hijack-popular-ai-model-on-hugging-face-platform", "title": "Researchers Hijack Popular AI Model on Hugging Face Platform", "summary": "Security analyst Alon Hertz manipulated a popular AI model on Hugging Face by altering only its neural weights, leaving the rest of the system untouched, and changed the model's voice output to produce poisoned audio in 87 seconds without modifying any code. The experiment demonstrates that weight-level tampering can compromise a hosted model's behavior while its surrounding code remains unchanged.", "body_md": "Meet Alon Hertz, a security analyst who pulled off a mind-blowing experiment: he manipulated a popular AI model's output by simply tweaking its neural weights, leaving the rest of the system untouched. In just 87 seconds, he altered the model's voice output to produce poisoned audio, all without changing a single line of code.", "url": "https://wpnews.pro/news/researchers-hijack-popular-ai-model-on-hugging-face-platform", "canonical_source": "https://osintsights.com/researchers-hijack-popular-ai-model-on-hugging-face-platform", "published_at": "2026-11-17 18:37:05+00:00", "updated_at": "2026-11-17 20:05:12.240727+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "machine-learning"], "entities": ["Alon Hertz", "Hugging Face"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/researchers-hijack-popular-ai-model-on-hugging-face-platform", "markdown": "https://wpnews.pro/news/researchers-hijack-popular-ai-model-on-hugging-face-platform.md", "text": "https://wpnews.pro/news/researchers-hijack-popular-ai-model-on-hugging-face-platform.txt", "jsonld": "https://wpnews.pro/news/researchers-hijack-popular-ai-model-on-hugging-face-platform.jsonld"}}