Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation
arXiv:2610.35910v1 Announce Type: new Abstract: Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can disparately affect vulnerable communities.…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-28 04:00 · arXiv cs.CV
Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation