arXiv AI
Steering Vision-Language Models for Visual-Contextual Privacy in Location Disclosure
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 21
Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models
arXiv:2609.21363v1 Announce Type: cross Abstract: Multimodal large reasoning models (MLRMs) have demonstrated remarkable capabilities in complex visual understanding. However, this very power introdu...
arXiv Computer Vision
Oct 16
AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO
The paper introduces KoreaGEO, a fine‑grained, multimodal, privacy‑aware benchmark for image‑based geolocation built from Korean street views. It covers four socio‑spatial clusters, nine place types, and includes two captioning styles that mimic real‑world privacy exposure. Using a three‑path protocol (image‑only, functional‑caption, high‑risk‑caption), the study shows that input modality has a stronger effect on localization accuracy and privacy risk than model size or architecture, and reveals structural prediction biases toward core cities.
arXiv Computer Vision
Oct 15
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
arXiv:2610.20055v1 Announce Type: new Abstract: The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses ser...
arXiv AI
Sep 1
Defending Wearable VLMs Against Private Attribute Inference
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
arXiv Machine Learning
Aug 20
On the Robustness of Vision-Language Models in Zero-shot Privacy Classification
The paper investigates whether large, instruction‑following Vision‑Language Models (VLMs) can reliably perform zero‑shot image privacy classification. It compares three open‑source VLMs to specialized privacy models on two public benchmarks, evaluating accuracy, robustness to image degradations (compression, lighting changes, noise), inference speed, and parameter count. The findings show that while VLMs remain robust to perturbations, they are less accurate and significantly slower than smaller, purpose‑built privacy models, indicating that scaling alone does not guarantee effective privacy classification.
arXiv AI
Jun 9
Vision Language Model Helps Private Information De-Identification in Vision Data
arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.