arXiv:2602.07815v3 Announce Type: replace Abstract: Facial age estimation plays a critical role in content moderation, age verification, and deepfake detection. However, no prior benchmark has system...
arXiv:2608.30210v1 Announce Type: cross Abstract: AI image generators now create face portraits that are hard to tell from real photographs. Vision-language models (VLMs) are increasingly proposed to...
The study audits four image aesthetic scorers—LAION-Aesthetics, PickScore, ImageReward, and HPSv2—using pixel‑level interventions on skin tone and body type in both synthetic and real images. It finds that most scorers exhibit a fidelity preference: unaltered images receive the highest scores, while perturbations in either direction are penalized in an inverted‑U pattern, and this effect is largely independent of the skin operator. Synthetic‑only audits are misleading, as the apparent preference for darker skin in synthetic faces reverses or weakens when evaluated on real faces, and cross‑scorer results vary widely, underscoring the need for real‑data, within‑image causal isolation to accurately assess demographic bias.
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.
arXiv:2608.21009v1 Announce Type: new Abstract: Ensuring that Extended Reality (XR) environments are age-appropriate is an important regulatory and safety challenge. However, current age assurance op...
arXiv:2607. 22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation.
arXiv:2610.19717v1 Announce Type: new Abstract: Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avat...
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
arXiv:2407. 13922v3 Announce Type: replace-cross Abstract: Face recognition (FR) systems are widely deployed in critical applications, making their reliability and robustness across diverse populations and conditions essential.
FusionAudit introduces PaRMA, a pathway-conditioned robustness auditing framework for native multimodal vision‑language models. It evaluates two image‑level interventions—pixel perturbation and rendered‑text insertion—to expose architecture‑specific blind spots. The study applies diagnostic‑motivated attacks (MANTIS and Nat‑Evid) to 18 open‑weight VLMs, revealing that legacy single‑attack rankings are unstable and that PaRMA uncovers higher residual risk than standard benchmarks.
arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.
arXiv:2609.23596v1 Announce Type: cross Abstract: With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models...