← Back to all news
arXiv AI By Leon Ranke, Wolfgang H\"ubner, Ronny Hug, Michael Arens, J\"urgen Beyerer

Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations

Read the original on arXiv AI →

The paper argues that evaluating privacy‑enhancing technologies (PETs) solely through image classification is insufficient because classification remains robust to many geometric and local perturbations. It proposes a compute‑aware multi‑task protocol that uses lightweight proxy tasks to assess PETs across various transformations, revealing that PETs with similar classification accuracy can perform very differently on other vision tasks. The study demonstrates the necessity of broader evaluation metrics beyond classification to truly gauge PET effectiveness.

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.

Related stories

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.

By Alina Elena Baia, Alessio Xompero, Andrea Cavallaro
llmsefficiencymultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
3d ago

HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework

HeteroPROMPT is a real‑time, privacy‑preserving framework for heterogeneous collaborative perception in autonomous systems. It aligns features from diverse sensors and models into a unified ego‑centric space using modular prompts and lightweight tuning, while keeping encoders and fusion stacks frozen. The system employs a metadata‑free autoencoder for modality classification and routing, achieving higher average precision on OPV2V‑H and V2XSet datasets with far fewer trainable parameters.

By Armin Maleki, Hayder Radha
agentsbenchmarkssafety
More like this →