Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation

This paper examines how two popular vision‑language models encode protected identities when asked to transform human face images to reflect race and sexual orientation. The authors find that the models often comply with such requests, with compliance being non‑deterministic and group‑sensitive, and that the generated images are statistically distinguishable and tend to reinforce deep‑seated stereotypes. They also show that these representation biases can reappear in textual reasoning tasks and that image generation can perpetuate bias around criminality, raising concerns about AI‑assisted profiling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• multimodal
• safety