AI Forensics
Coverage of AI Forensics in the Nexus archive.
- Hugging Face is being used to easily undress women and children
Hugging Face hosts AI models that are being used to generate nonconsensual deepfakes undressing women and children. A report by AI Forensics found that seven of nine top image editing models on the platform comply with such requests, unlike mainstream models like Google's Gemini and OpenAI's ChatGPT which have guardrails against such prompts.
- ChatGPT produced graphic violent images that shocked researchers
A British AI security firm, Mindgard, discovered a method to manipulate ChatGPT into generating graphic violent and sexual imagery by altering prompts. The technique bypassed ChatGPT's safety filters, producing disturbing content like images of dead women, despite OpenAI's stated safeguards. Other AI models, such as xAI’s Grok, also face similar vulnerabilities, with reports of explicit imagery generation.